Browse popular Model Context Protocol servers and connect them to your Seclai agents. Pick a server to add it — managed servers connect with one click, others use your own credentials. Many entries list the tools the server exposes so you know what your agents can do before you connect.
Provides access to pre-trained machine learning models and datasets for natural language processing, computer vision, and other AI tasks.
Tools (8)
hf_whoamiHugging Face tools are being used anonymously and may be rate limited. Call this tool for instructions on joining and authenticating.
space_searchFind Hugging Face Spaces using semantic search. IMPORTANT Only MCP Servers can be used with the dynamic_space toolInclude links to the Space when presenting the results.
hub_repo_searchSearch Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or aggregate across multiple repo types in one call. Use space_search for semantic-first discovery of Spaces. Include links to repositories in your response.
paper_searchFind Machine Learning research papers on the Hugging Face hub. Include 'Link to paper' When presenting the results. Consider whether tabulating results matches user intent.
hub_repo_detailsGet details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified. For datasets, use operations: overview, dataset_structure, dataset_preview. Use dataset_structure first to discover configs, splits, sizes, and schema. Use dataset_preview only when config and split are known, unless the dataset has a single config/split.
hf_doc_searchSearch and Discover Hugging Face Product and Library documentation. Send an empty query to discover structure and navigation instructions. Knowledge up-to-date as at 4 June 2026. Combine with the Product filter to focus results.
hf_doc_fetchFetch a document from the Hugging Face or Gradio documentation library. For large documents, use offset to get subsequent chunks.
gr1_z_image_turbo_generateGenerate an image using the Z-Image model based on the provided prompt and settings. This function is triggered when the user clicks the "Generate" button. It processes the input prompt (optionally enhancing it), configures generation parameters, and produces an image using the Z-Image diffusion transformer pipeline. Returns: tuple: (gallery_images, seed_str, seed_int), - seed_str: String representation of the seed used for generation, - seed_int: Integer representation of the seed used for generation (from mcp-tools/Z-Image-Turbo)
Manage your Seclai agents, knowledge bases, content sources, governance policies, and alerts from an agent.
Tools (10)
list_agentsList the agents in your account.
create_agentCreate a new agent from a workflow definition.
run_agentRun an agent with an input and return its output.
get_agent_run_statusCheck the status and full trace of an agent run.
searchSemantic search across your knowledge bases.
chat_with_knowledge_baseAsk a question and get a grounded answer from a knowledge base.
list_governance_evaluationsReview content-governance evaluations and their verdicts.
create_governance_policyCreate a content-governance policy.
list_alertsList triggered alerts across your agents and sources.
create_sourceAdd a website or RSS content source to pull from on a schedule.
Google Cloud BigQuery BigQuery: Advanced analytical insights for agents.
Tools (6)
list_dataset_idsList BigQuery dataset IDs in a Google Cloud project.
get_dataset_infoGet metadata information about a BigQuery dataset.
list_table_idsList table ids in a BigQuery dataset.
get_table_infoGet metadata information about a BigQuery table.
execute_sql_readonlyRun a read-only SQL query in the project and return the result. Prefer this tool over `execute_sql` if possible. This tool is restricted to only `SELECT` statements. `INSERT`, `UPDATE`, and `DELETE` statements and stored procedures aren't allowed. If the query doesn't include a `SELECT` statement, an error is returned. For information on creating queries, see the [GoogleSQL documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax). Example Queries: -- Count the number of penguins in each island. SELECT island, COUNT(*) AS population FROM bigquery-public-data.ml_datasets.penguins GROUP BY island -- Evaluate a bigquery ML Model. SELECT * FROM ML.EVALUATE(MODEL…
execute_sqlRun a SQL query in the project and return the result. Prefer the `execute_sql_readonly` tool if possible. This tool can execute any query that bigquery supports including: * SQL Queries (SELECT, INSERT, UPDATE, DELETE, CREATE, etc.) * AI/ML functions like AI.FORECAST, ML.EVALUATE, ML.PREDICT * Any other query that bigquery supports. Example Queries: -- Insert data into a table. INSERT INTO `my_project.my_dataset`.my_table (name, age) VALUES ('Alice', 30); -- Create a table. CREATE TABLE `my_project.my_dataset`.my_table ( name STRING, age INT64); -- DELETE data from a table. DELETE FROM `my_project.my_dataset`.my_table WHERE name = 'Alice'; -- Create Dataset CREATE SCHEMA…
Search domains and check availability.
Tools (2)
domains_suggestGenerate domain name suggestions based on keywords, seed domains, or business descriptions. Returns an interactive widget with clickable domain links for clients that support HTML rendering (browsers, web-based AI assistants), with automatic fallback to formatted text for other clients. IMPORTANT: Always display the registration links from the response to the user - each domain has a direct GoDaddy registration URL that must be shown.
domains_check_availabilityCheck if domain names are available for registration. Works with single domains or lists of multiple domains. Returns formatted results with availability status and registration options ready for display. IMPORTANT: Always display the registration links from the response to the user - each domain has a direct GoDaddy registration URL that must be shown.
Allows users to discover, book, and purchase tickets for activities, tours, and experiences at attractions worldwide.
Tools (6)
experience_availabilityGet availability information for a specific experience including dates, times, and pricing
experience_detailsGet detailed information about a specific experience by ID
list_tagsList all category tags
render_activity_tilesRender activity tiles for a list of activity IDs, returning an embeddable widget URI
search_experiencesSearch for travel experiences with comprehensive filtering options. Returns available categories, tags, and regions with IDs for further filtering.
search_regionsSearch for regions by name
Booking Assistance Find & book local Taskrabbit services near you.
Tools (3)
check_service_availabilityCheck availability, pricing, and scoping questions for a service in a location. Provide either city + state OR postalCode to specify the location.
generate_deep_linkGenerate a pre-filled Taskrabbit booking deep link using task template ID.
list_supported_servicesList Taskrabbit services available in a location. Provide either city + state OR postalCode.
Google Cloud BigQuery BigQuery: Advanced analytical insights for agents.
Tools (6)
list_dataset_idsList BigQuery dataset IDs in a Google Cloud project.
get_dataset_infoGet metadata information about a BigQuery dataset.
list_table_idsList table ids in a BigQuery dataset.
get_table_infoGet metadata information about a BigQuery table.
execute_sql_readonlyRun a read-only SQL query in the project and return the result. Prefer this tool over `execute_sql` if possible. This tool is restricted to only `SELECT` statements. `INSERT`, `UPDATE`, and `DELETE` statements and stored procedures aren't allowed. If the query doesn't include a `SELECT` statement, an error is returned. For information on creating queries, see the [GoogleSQL documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax). Example Queries: -- Count the number of penguins in each island. SELECT island, COUNT(*) AS population FROM bigquery-public-data.ml_datasets.penguins GROUP BY island -- Evaluate a bigquery ML Model. SELECT * FROM ML.EVALUATE(MODEL…
execute_sqlRun a SQL query in the project and return the result. Prefer the `execute_sql_readonly` tool if possible. This tool can execute any query that bigquery supports including: * SQL Queries (SELECT, INSERT, UPDATE, DELETE, CREATE, etc.) * AI/ML functions like AI.FORECAST, ML.EVALUATE, ML.PREDICT * Any other query that bigquery supports. Example Queries: -- Insert data into a table. INSERT INTO `my_project.my_dataset`.my_table (name, age) VALUES ('Alice', 30); -- Create a table. CREATE TABLE `my_project.my_dataset`.my_table ( name STRING, age INT64); -- DELETE data from a table. DELETE FROM `my_project.my_dataset`.my_table WHERE name = 'Alice'; -- Create Dataset CREATE SCHEMA…
Excalidraw MCP for creating interactive hand-drawn diagrams in Excalidraw.
Tools (5)
read_meReturns the Excalidraw element format reference with color palettes, examples, and tips. Call this BEFORE using create_view for the first time.
create_viewDraw DiagramRenders a hand-drawn diagram using Excalidraw elements. Elements stream in one by one with draw-on animations. Call read_me first to learn the element format.
export_to_excalidrawUpload diagram to excalidraw.com and return shareable URL.
save_checkpointUpdate checkpoint with user-edited state.
read_checkpointRead checkpoint state for restore.
Add authentication, organizations, and billing.
Tools (2)
clerk_sdk_snippetClerk SDK snippetGet Clerk SDK code snippets and patterns.
list_clerk_sdk_snippetsList Clerk SDK snippetsList all available Clerk SDK snippets and bundles. Filter by tag to find specific functionality.
Creates searchable indexes of code repositories to help understand and navigate codebases.
Tools (3)
read_wiki_structureGet a list of documentation topics for a GitHub repository. Args: repoName: GitHub repository in owner/repo format (e.g. "facebook/react")
read_wiki_contentsView documentation about a GitHub repository. Args: repoName: GitHub repository in owner/repo format (e.g. "facebook/react")
ask_questionAsk any question about a GitHub repository and get an AI-powered, context-grounded response. Args: repoName: GitHub repository or list of repositories (max 10) in owner/repo format question: The question to ask about the repository
Retrieves up-to-date documentation from public and private libraries to provide AI coding agents with current API references and code examples.
Tools (2)
search_docsSearch DocumentationSearch a library's indexed documentation and return relevant sections with titles, summaries, and URLs. Results are sourced from official, versioned documentation. Usage: - Be specific in your query. Include the feature, API, or concept you need. Good: "server-side rendering with App Router". Bad: "rendering". - The library parameter accepts a simple name (e.g., react, nextjs) or exact owner/repo for precision (e.g., vercel/next.js, TanStack/query). - When multiple library candidates appear, prefer exact name matches and official organizations over forks. - After 2 searches without finding the relevant section, switch to fetch_doc on the best result URL or the library's documentation root…
fetch_docFetch DocumentationRetrieve full documentation content from a URL and return it as rendered markdown. Use this tool to get complete pages — including code examples, API signatures, and prose — from search_docs result URLs. - Pass a URL directly from search_docs results to retrieve that section's full content. - Trim the URL anchor or path to a parent directory to get a broader table of contents with section previews. - Returns rendered markdown that preserves code blocks, headings, and document structure. - Only works on Docfork-indexed documentation — use WebFetch for URLs not returned by search_docs. - If search_docs returns sparse or no results, try fetch_doc on the library's root documentation URL (e.g.…
GraphOS MCP Tools Search Apollo docs, specs, and best practices.
Tools (3)
ApolloConnectorsSpecThis tool provides the agent with the specification which describes how to use Apollo Connectors in a graphql schema to send an HTTP request or use any REST API with a graph. A user may refer to an Apollo Connector as 'Apollo Connector', 'REST Connector', or even just 'Connector'. Treat these all as synonyms for the same thing. You MUST ALWAYS call this tool to use this specification as a guide BEFORE planning, making, or proposing ANY edits or additions to a connectors schema file and/or a graphql file containing @connect or @source. This tool is to provide the agent with guidance, not the user.
ApolloDocsReadFetches the complete markdown content of an Apollo documentation page using its slug, or everything after https://apollographql.com/docs. Documentation slugs can be obtained from the SearchDocs tool results. Use this after ApolloDocsSearch to read full pages rather than just excerpts. Content will be given in chunks with the totalCount field specifying the total number of chunks. Start with a chunkIndex of 0 and fetch each chunk.
ApolloDocsSearchSearches official Apollo GraphQL documentation (Apollo GraphQL, GraphOS, Apollo Router, Apollo Client, API orchestration, MCP Server, schema design, deployment best practices, connectors, and platform usage). Returns url, slug, and markdown content excerpts. For complete page content, you MUST use the returned slug with the ApolloDocsRead tool. Use this tool when you need technical information, configuration examples, best practices, and troubleshooting guides for any Apollo GraphQL technology. Use the ApolloDocsRead tool to get all of the content for a given search result using the slug, don't use a WebSearch.
Provides searchable access to Java API documentation for libraries and frameworks.
Tools (8)
get_latest_versionResolves the latest published version of a Maven Central artifact (any groupId:artifactId — Java, Kotlin, or Scala library). Call this first when you only know the artifact but not the version: the version it returns feeds into every other tool here that takes a concrete version. Works against the live Maven Central catalog — no local install, build tool, or repository checkout required.
get_javadoc_indexFetches the rendered Javadoc/Scaladoc index page for a specific Maven Central artifact version, converted to plain text/markdown. Useful for orienting yourself in an unfamiliar library: it lists the top-level packages, modules, and (for Scaladoc) often a curated overview. Use this before drilling into specific symbols. Works against the live Maven Central catalog — you do not need to download the javadoc jar.
get_javadoc_content_listLists every entry in the Javadoc/Scaladoc jar of a Maven Central artifact version (HTML pages for classes/methods/packages, plus search-index files and resources). Each returned `link` can be passed to get_javadoc_symbol_contents to read the rendered API doc as text/markdown. Use this when you need to discover what a library documents and then read those docs without leaving the agent loop. If this returns NotFoundError (some libraries don't publish a javadoc jar — e.g. some ZIO releases) fall back to list_source_contents to read the raw source instead.
get_javadoc_symbol_contentsReads one Javadoc/Scaladoc page from a Maven Central artifact, already converted to plain text/markdown so you don't have to parse HTML. Pass the `link` value returned by get_javadoc_content_list. Use this when you need to know what a class, method, or field does and what its parameters mean for any library on Maven Central — without downloading or unzipping the javadoc jar yourself.
get_source_contentsReads one source file from a Maven Central library's sources jar (the `-sources.jar` artifact). Pass the `link` value returned by list_source_contents. Use this whenever you need the exact source text of a JVM library — tracing behavior into a dependency, confirming a public API's implementation, finding a definition, or comparing two library versions. Strongly preferred over locating the jar in a local build cache and unzipping it: it works for any Maven Central artifact, no local checkout or build needed.
list_source_contentsLists every file inside the **sources jar** (the `-sources.jar` publishers attach alongside the binary) of a Maven Central artifact version. Each returned path can be fed to get_source_contents to read the file. Prefer this any time you would otherwise locate a `-sources.jar` in your local Coursier/Ivy/Maven cache and `unzip` it: this tool works directly against Maven Central, requires no local install or build, and works for libraries you've never depended on. Use it whenever you need to read the actual source of a JVM library (Java, Kotlin, Scala) — for example to understand an implementation detail, find where a method is defined, see how a feature is wired internally, or work with a…
search_artifactsSearches the indexed Maven Central catalog for artifacts whose groupId or artifactId contains a substring (case-insensitive). Use this when you know part of a library name (e.g. "jackson", "zio-http", "netty-codec") and need the exact groupId:artifactId coordinates to feed into the other tools. Pair with get_latest_version once you've picked an artifact.
symbol_to_artifactResolves a class name, fully-qualified type, or package name to the Maven Central artifact (groupId, artifactId) that publishes it. Case-sensitive. Use this when you have a symbol from a stack trace, an import line, or an error message and you need to know which library to look in. From there, chain into get_latest_version, then list_source_contents / get_javadoc_content_list to read the code or docs.
Validates Mermaid syntax, renders diagrams as high-quality SVG, and displays them instantly in an interactive UI where users can preview, zoom, and iterate.
Tools (17)
validate_and_render_mermaid_diagramSIMPLE RENDER TOOL - Renders Mermaid diagrams directly (Mermaid automatically validates during rendering). If successful, returns diagram image. If Mermaid validation fails, returns error details for fixing. One tool, one call, simple workflow.
get_diagram_titleGenerate a descriptive title for a Mermaid diagram based on its content. This tool analyzes the diagram structure and content to suggest an appropriate title.
get_diagram_summaryGenerate a concise summary for a Mermaid diagram based on its content. This tool provides prompts for the LLM to generate a brief summary (2-4 sentences) highlighting the primary flow, key decisions, and outcomes.
search_mermaid_iconsSearch for available Mermaid icons by provider or name. Returns icons in ready-to-use format with provider prefixes (e.g., 'aws:arch-amazon-ec2'). PERFORMANCE TIP: For faster searches, start with limit=10 and specific queries. If no suitable icons found, increase limit and retry. Supports AWS, Azure, GCP, and FontAwesome icon sets.
get_mermaid_syntax_documentGet comprehensive syntax documentation and examples for a specific Mermaid diagram type. Returns the official Mermaid.js documentation with syntax rules, examples, and usage instructions for the requested diagram type.
list_toolsLists all available MCP servers and their tools in the workspace.
list_reposList GitHub repositories for the authenticated user, or for an organization when `org` is set. REQUIRES: `Github-Token` header (HTTP) or `GITHUB_TOKEN` / `GH_TOKEN` in the server environment.
list_mermaid_filesList .mmd Mermaid files in a GitHub repository (code search with tree fallback). REQUIRES: `Github-Token` header (HTTP) or GITHUB_TOKEN / GH_TOKEN.
read_mermaid_fileRead a single .mmd file from a GitHub repository. Only paths ending in .mmd are allowed. REQUIRES: `Github-Token` header (HTTP) or GITHUB_TOKEN / GH_TOKEN.
create_prCreate a new branch (git ref), one commit from the base tree with your file changes, then open a pull request in the same repository. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN with `contents: write` (and no existing branch with the same `headBranch` name).
push_fileCreate or update a single file on a given branch in a GitHub repository. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN with contents write access.
list_pullsList pull requests for a GitHub repository. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN / GH_TOKEN.
list_branchesList or resolve branch names. **List mode (default):** one `GET /repos/.../branches?per_page=100&page=1` — at most 100 names, A–Z sorted in the response; `has_more` if a full page was returned. **Resolve mode:** set `branch_name` for a single `GET` branch (404 if missing). At most one GitHub API call. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN / GH_TOKEN.
list_issuesList issues for a repository (excludes pull requests). REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN / GH_TOKEN.
create_issueCreate an issue in a GitHub repository. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN with issues write if creating issues in private repos.
get_issue_commentsList comments on an issue by issue number. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN / GH_TOKEN.
get_pull_commentsGet all pull request comments: both issue/PR thread comments and inline review comments, with a `type` of `issue_thread` or `review` per item. REQUIRES: `Github-Token` (HTTP) or GITHUB_TOKEN / GH_TOKEN.
Search trusted Microsoft docs to power your development.
Tools (3)
microsoft_docs_searchMicrosoft Docs SearchSearch official Microsoft/Azure documentation to find the most relevant and trustworthy content for a user's query. This tool returns up to 10 high-quality content chunks (each max 500 tokens), extracted from Microsoft Learn and other official sources. Each result includes the article title, URL, and a self-contained content excerpt optimized for fast retrieval and reasoning. Always use this tool to quickly ground your answers in accurate, first-party Microsoft/Azure knowledge. ## Follow-up Pattern To ensure completeness, use microsoft_docs_fetch when high-value pages are identified by search. The fetch tool complements search by providing the full detail. This is a required step for…
microsoft_code_sample_searchMicrosoft Code Sample SearchSearch for code snippets and examples in official Microsoft Learn documentation. This tool retrieves relevant code samples from Microsoft documentation pages providing developers with practical implementation examples and best practices for Microsoft/Azure products and services related coding tasks. This tool will help you use the **LATEST OFFICIAL** code snippets to empower coding capabilities. ## When to Use This Tool - When you are going to provide sample Microsoft/Azure related code snippets in your answers. - When you are **generating any Microsoft/Azure related code**. ## Usage Pattern Input a descriptive query, or SDK/class/method name to retrieve related code samples. The optional…
microsoft_docs_fetchMicrosoft Docs FetchFetch and convert a Microsoft Learn documentation webpage to markdown format. This tool retrieves the latest complete content of Microsoft documentation webpages including Azure, .NET, Microsoft 365, and other Microsoft technologies. ## When to Use This Tool - When search results provide incomplete information or truncated content - When you need complete step-by-step procedures or tutorials - When you need troubleshooting sections, prerequisites, or detailed explanations - When search results reference a specific page that seems highly relevant - For comprehensive guides that require full context ## Usage Pattern Use this tool AFTER microsoft_docs_search when you identify specific…
Provides audited smart contract libraries for Cairo to build secure applications on StarkNet and other Cairo-based blockchains.
Tools (8)
cairo-erc20Make a fungible token per the ERC-20 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-erc721Make a non-fungible token per the ERC-721 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-erc1155Make a non-fungible token per the ERC-1155 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-accountMake a custom smart contract that represents an account that can be deployed and interacted with other contracts, and can be extended to implement custom logic. An account is a special type of contract that is used to validate and execute transactions. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-multisigMake a multi-signature smart contract, requiring a quorum of registered signers to approve and collectively execute transactions. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-governorMake a contract to implement governance, such as for a DAO. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-vestingMake a vesting smart contract that manages the gradual release of ERC-20 tokens to a designated beneficiary based on a predefined vesting schedule. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-customMake a custom smart contract. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
Provides a directory of MCP servers that connect AI agents like Claude and ChatGPT to third-party services and tools.
Tools (1)
ListRemoteMCPServersList and search for trusted Remote MCP Servers from https://github.com/jaw9c/awesome-remote-mcp-servers and https://remote-mcp.com
Estimate your federal & state taxes with Aiwyn's tax engine.
Tools (10)
check_taxCheck inputs to calculate a tax return for a given jurisdiction. The 'input' argument must conform to the JSON schema returned by the tax_namespace_schema tool. Returns 'Success' on success, or validation errors if the input is invalid. If some inputs trigger a PARTIAL DISQUALIFICATION, the check still succeeds but includes disqualification details — proceed to calculate_tax to get the document and estimate the impact. Use this tool to validate inputs before calculating the tax return.
calculate_taxCalculate a tax return for a given jurisdiction. The 'input' argument must conform to the JSON schema returned by the tax_namespace_schema tool. Returns computed tax return document on success, or validation errors if the input is invalid. If some inputs trigger a PARTIAL DISQUALIFICATION, the document is still returned for the supported fields; review the disqualification details and estimate the impact of the unsupported fields on the taxpayer's tax owed or refund due. Use the check_tax tool first to validate the input before calculating the tax return with this tool.IMPORTANT RULES: (1) All field values must be wrapped as {"value": <val>} — never pass bare values. (2) Currency amounts…
tax_yearsList all supported tax years.
tax_jurisdictionsList all supported tax jurisdictions for a given tax year.
tax_namespace_schemaGet the TCB input schema for a single namespace (e.g. "irs1040", "irs1040_schedulec", "ca_form540"). Returns the properties and types for that namespace. HOW TO READ THE SCHEMA: (1) Each field references a type like tcb_string_null, tcb_integer_null, or tcb_boolean_null. All values must be wrapped as {"value": <val>}. (2) If the namespace title ends in '_list' (e.g. 'w2_list', 'dependent_detail_list'), it is a NamespaceList — an array of objects. Each array item MUST include a "uuid" field (non-null UUIDv4 string). (3) Reference fields link entries to other namespaces e.g. "person" in qualifying_person_grp, "student" in student_educational_instn_grp. All use the same format: {"value":…
tax_namespacesList all available input namespaces for a given jurisdiction. Use the returned names with the tax_namespace_schema tool to get the schema for a specific namespace. Requires a jurisdiction (e.g. "us" for federal, "ca" for California). Use the tax_jurisdictions tool first to discover available jurisdictions. NAMESPACE NAMING CONVENTIONS: Federal namespaces: irs1040, irs1040_schedule1, irs8962, w2, dependent_detail, etc. State namespaces: always prefixed with the state abbreviation (ca_form540, ny_it201, az_form140). NAMESPACE TYPES: Some namespaces are singletons (object), others are NamespaceLists (array) that can hold multiple items — e.g. w2 (multiple W-2s), dependent_detail (multiple…
tax_simple_returnCall this FIRST when beginning any tax return. Returns the curated namespace list, top-level structure guide, example input, and step-by-step filing workflow. By default returns a simple scenario (single or MFJ filer, W-2 income only, standard deduction, no dependents). Pass scenario="with_dependents" for returns that include dependents, child care (Form 2441), and education credits (Form 8863). Optionally pass a state jurisdiction (e.g. "ca") to also include state-level namespaces — if you don't know which state applies, ask the user before calling.
generate_tax_pdf_toolStart async PDF generation for a tax return. The 'input' argument must conform to the JSON schema returned by the tax_namespace_schema tool. Returns a job ID to poll with get_tax_pdf.Use the check_tax tool first to validate the input before generating the tax PDF with this tool.The input follows the same rules as calculate_tax: all values wrapped as {"value": <val>}, array items require UUIDv4 fields (extended link items use UUIDv5), references use who_applies_to, and return_header is top-level (not inside return_data). Use tax_simple_return to see the full input structure.
get_tax_pdf_toolCheck status of a PDF generation job. Returns the status and a download URL when completed, only use this tool after generating the tax PDF with the generate_tax_pdf tool and it successfully returns a job ID. When returning the url of the PDF inform the user that I'm just a tax estimator, you should consult with a tax professional.
generate_uuid_v5Generate a UUID v5 based on a source uuid and namespace.
Simulate fund classifications under proposed SFDR 2.0.
Tools (6)
search_securitiesSearch SecuritiesSearch securities by keyword, ISIN, or CUSIP through the upstream Clarity SFDR demo API.
sfdr20_assess_fund_nameSFDR 2.0 Check by Fund NamePreferred for fund names, partial names, and natural-language requests. Resolve a fund from free-text (for example S&P 500 or Nordea 1 Global Climate and Environment), then run the SFDR20 check and return an interpreted assessment. Example: use this for 'Show the SFDR 2.0 category assessment evidence for Nordea 1 Global Climate and Environment Fund'.
sfdr20_check_by_isinSFDR 2.0 Check by ISINUse only when the user already provided an explicit ISIN. Do not use for fund names, partial names, or natural-language fund requests; use sfdr20_assess_fund_name instead.
sfdr20_check_by_querySFDR 2.0 Check by Fund Name (Legacy Alias)Deprecated alias for sfdr20_assess_fund_name. Keep for backward compatibility only. Prefer sfdr20_assess_fund_name for fund names and natural-language requests.
sfdr20_checkSFDR 2.0 Check by ISIN (Legacy Alias)Deprecated alias for sfdr20_check_by_isin. Keep for backward compatibility only. Do not use for fund names or natural-language requests.
interpret_sfdr20_resultInterpret SFDR 2.0 ResultNormalize raw SFDR20 flags into category-level assessment evidence.
Crypto.com Real time prices, orders, charts, and more for crypto.
Tools (9)
get_index_priceIndex price for an instrument
get_tickerSingle ticker for an instrument
get_instrumentInstrument detail for an instrument by id
get_tradesRecent trades (default 10, max 150)
get_mark_priceMark price for an instrument
get_bookOrder book snapshot (bids/asks)
get_tickersTickers for an instrument or all
get_instrumentsList all available trading instruments
get_candlestickRecent candlesticks for an instrument and timeframe (returns up to 50)
Discover every grant opportunity in existence..
Tools (5)
search_grantsSearch GrantsSearch 84,000+ grant opportunities by keyword, state, source type, funder, and more. Uses semantic search (embeddings + full-text + scoring) combined with live AI-powered web discovery for comprehensive results. Returns active grants ranked by relevance with fit scores, deadlines, amounts, and application links. Use this as the starting point to find relevant grants.
get_grantGet Grant DetailsGet full details for a specific grant by its slug. Returns eligibility criteria, application link, deadline, amount, funder info, and tags. Use search_grants first to find valid slugs.
search_fundersSearch FundersSearch 133,000+ US foundations by name, state, NTEE code, asset range, and annual income range. Returns key metrics: name, state, total assets, annual income (from IRS 990), NTEE category, and mission. Use get_funder with the returned slug for full profiles including actual giving history.
get_funderGet Funder ProfileGet a full foundation profile including mission, 5-year financials, recent grants awarded, key officers, and application info. Accepts a foundation slug (from search_funders results) or EIN (e.g. '13-1684331').
get_past_winnersGet Past WinnersCompetitive intelligence: see who has won a specific federal grant program. Shows top recipients grouped by organization with award counts, total funding, and year-over-year trends. Filter by CFDA number, agency, program name, or state. Supports agency abbreviations: NIH, NSF, EPA, DOE, DOD, USDA, NASA, SBA, etc.
Job search made easy.
Tools (1)
search_jobsDo not use this tool if the search is for jobs outside of the United States or Canada. Use this tool when the user expresses intent to find, search, browse, view, or compare job opportunities, for example, full-time roles, part-time positions, remote jobs, and many more. The user can find jobs by job title, skills, keywords, location, remote options, salary range, employment type, experience level, and posting recency. The tool works best when searching for a single job role at a time, so queries with multiple job roles will not produce expected results. STRICT ARGUMENT RULE: - Optional filters are opt-in only. The assistant must omit every optional filter unless the user explicitly stated…
Securely access Autodesk's help documentation.
Tools (2)
get_available_productsGet Available ProductsReturns the canonical Autodesk product catalog (closed set). Each item has: product_name, product_code, and release_codes. Use this to discover or validate product values for other product-scoped tools. Not required if valid product context is already available. Terminology: release_codes = the code only (e.g. 2025), not the human-readable release name (release_name, e.g. 'AutoCAD 2025').
search_help_contentSearch Help ContentSearch Autodesk Help/Support documentation and return the most relevant documents for a user question. Use when: - The user asks how to do something in an Autodesk product. - The user reports an error (include the exact error text/code in the query). - The user needs official troubleshooting steps or reference documentation. Call shape (recommended): - Always pass: `query`, `locale`. - If your agent has a default product context, pass it directly via `product_code` (preferred) or `product_name`. - Pass `release_code` only when you can validate it for that product. Behavior: 1) Locale: - Read `locale` from your current context. Do not guess locale. - Pass that locale as the `locale`…
Up-to-date docs for LLMs and AI code editors.
Tools (2)
resolve-library-idResolve Context7 Library IDResolves a package/product name to a Context7-compatible library ID and returns matching libraries. You MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Each result includes: - Library ID: Context7-compatible identifier (format: /org/project) - Name: Library or package name - Description: Short summary - Code Snippets: Number of available code examples - Source Reputation: Authority indicator (High, Medium, Low, or Unknown) - Benchmark Score: Quality indicator (100 is the highest score) - Versions: List of versions…
query-docsQuery DocumentationRetrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework. You must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Do not call this tool more than 3 times per question.
Search trusted Microsoft docs to power your development.
Tools (3)
microsoft_docs_searchMicrosoft Docs SearchSearch official Microsoft/Azure documentation to find the most relevant and trustworthy content for a user's query. This tool returns up to 10 high-quality content chunks (each max 500 tokens), extracted from Microsoft Learn and other official sources. Each result includes the article title, URL, and a self-contained content excerpt optimized for fast retrieval and reasoning. Always use this tool to quickly ground your answers in accurate, first-party Microsoft/Azure knowledge. ## Follow-up Pattern To ensure completeness, use microsoft_docs_fetch when high-value pages are identified by search. The fetch tool complements search by providing the full detail. This is a required step for…
microsoft_code_sample_searchMicrosoft Code Sample SearchSearch for code snippets and examples in official Microsoft Learn documentation. This tool retrieves relevant code samples from Microsoft documentation pages providing developers with practical implementation examples and best practices for Microsoft/Azure products and services related coding tasks. This tool will help you use the **LATEST OFFICIAL** code snippets to empower coding capabilities. ## When to Use This Tool - When you are going to provide sample Microsoft/Azure related code snippets in your answers. - When you are **generating any Microsoft/Azure related code**. ## Usage Pattern Input a descriptive query, or SDK/class/method name to retrieve related code samples. The optional…
microsoft_docs_fetchMicrosoft Docs FetchFetch and convert a Microsoft Learn documentation webpage to markdown format. This tool retrieves the latest complete content of Microsoft documentation webpages including Azure, .NET, Microsoft 365, and other Microsoft technologies. ## When to Use This Tool - When search results provide incomplete information or truncated content - When you need complete step-by-step procedures or tutorials - When you need troubleshooting sections, prerequisites, or detailed explanations - When search results reference a specific page that seems highly relevant - For comprehensive guides that require full context ## Usage Pattern Use this tool AFTER microsoft_docs_search when you identify specific…
Civil legal guidance for self-represented litigants.
Tools (3)
case_intake_assessmentAssesses a self-represented litigant's civil legal situation from their narrative and returns viability, likely claims, the correct court, and concrete first steps. Use it when a user describes a legal problem they are personally experiencing and wants to know whether they have a viable civil case, what legal claims or defenses may apply, what court would handle their matter, or what they should do first. Typical triggers: "my landlord won't return my deposit", "I got served with a lawsuit", "my employer owes me wages", "someone damaged my property and won't pay". Do NOT call this tool for criminal matters (DUI, assault, theft, etc.), immigration, bankruptcy, general legal questions not…
deadline_calculatorReturn critical procedural deadlines and consequences for a specific legal triggering event. Uses a precomputed lookup table — not LLM inference. Initial launch covers 15 states; the response includes a `coverage_note` field when state data is limited. Some jurisdictions count motion-response deadlines backward from the hearing date rather than forward from service. When a backward-counting deadline applies, the tool requires a hearing_date input and calculates the due date relative to it. Use this tool when a user mentions a specific legal event that has already occurred and needs to know what deadlines apply. Typical triggers: "I was just served — how long do I have?", "they filed a…
next_step_guidanceReturn the 2–3 most important actions for a self-represented litigant who is already in active civil litigation and knows their case stage. Use this tool when a user is mid-case — they have already filed or been served, and want to know what to do next. Typical triggers: "I already filed my answer, now what?", "the discovery period just started", "we have a pretrial conference coming up". Do NOT use when the user hasn't started litigation (use `case_intake_assessment`), when asking about a specific deadline event (use `deadline_calculator`), or when asking about a new unrelated legal problem. Each step includes an accelerator_module field naming one of Courtroom5's four LAW Accelerator…
Ground your work in clean, structured U.S. primary law.
Tools (13)
analyze_legal_questionAnalyze Legal QuestionAssess a broad or fact-dependent legal research question before searching to identify the jurisdiction, facts, legal issue, and procedural context needed for useful research. Returns ready_for_research or needs_clarification with up to three short clarifying questions.
search_cases_by_conceptSearch Cases by ConceptUse this first when the user wants to find leading or relevant cases about a legal issue, doctrine, fact pattern, jurisdiction, claim, defense, or topic and does not already have a Descrybe case_id. Results are authority-ranked by default to surface stronger legal authorities before ordinary text matches. Use date sorting only when the user asks for recent or newest cases. Each result includes case_id, the Descrybe canonical identifier accepted by known-case tools.
search_laws_and_rulesSearch Laws and RulesSemantic/concept search over U.S. non-case primary law, including statutes, regulations, and constitutional provisions. Useful for legal rules outside judicial opinions when the issue, rule, citation, or topic can be described in natural language. Results are ranked by concept similarity and returned with compact matched source passages.
search_case_textSearch Case TextSearches the full text of judicial opinions by exact words or phrases across Descrybe's case-law text index. Useful when specific language matters, such as terms of art, quotes, statutory phrases, or uncommon factual wording. Each result includes case_id, the Descrybe canonical identifier accepted by known-case tools.
find_case_from_referenceFind Case from ReferenceResolves a citation, case name, case caption, party name, party-name variant, docket number, short cite, quote, or mixed reference into a Descrybe case or candidate set. Use this for party-name or docket-number case lookup when the user does not already have a Descrybe case_id. Resolved cases and candidates include case_id, the Descrybe canonical identifier accepted by known-case tools. The context_text field can improve short, bare, or ambiguous references.
extract_case_referencesExtract Case ReferencesExtracts case-law citations and references from legal text provided in the text argument. Returns one item per unique resolved case or best unresolved reference cluster, with occurrence counts, raw citations seen, and tagged excerpts. When resolve=true, results include compact case-identity resolution and a quick treatment indicator for each resolved case, including case_id when a Descrybe case is resolved. This does not verify quotes, analyze support, or return a full citing-case treatment map.
get_case_summaryGet Case SummaryRetrieves the precomputed standard or simplified summary for a known Descrybe case's primary opinion. Requires a Descrybe case_id; for legal research, prefer the standard summary unless the user asks for a simplified or plain-language explanation.
get_case_passagesGet Case PassagesReturns a small ranked list of focused raw passages from a known Descrybe case's primary opinion. Requires a Descrybe case_id and a focus issue, phrase, rule, quote, or fact pattern. This is not a full-opinion fetch and does not return every occurrence.
get_case_detailsGet Case DetailsRetrieves case metadata, summary availability, opinion inventory, and treatment summary for a known Descrybe case. Requires a Descrybe case_id.
check_case_statusCheck Case StatusChecks a known Descrybe case for a quick treatment/status signal before relying on it. Requires a Descrybe case_id. Returns whether later cases appear to treat the case positively, negatively, cautiously, or neutrally, plus a rough authority-weight label. This is a fast status check, not a full citing-case map and not a forum-specific binding analysis.
find_cases_that_citeFind Cases That CiteFinds later cases that cite a known Descrybe case. Requires a Descrybe case_id. Useful for updating research, finding treatment, or locating newer authority that follows, distinguishes, or discusses the case. Returned citing cases include case_id when a Descrybe case is identified.
verify_quoteVerify QuoteVerifies whether quoted language appears in a known Descrybe case and locates the matching opinion. Requires a Descrybe case_id and exact or near-exact quote text. Returns whether the quote was found, where it matched, and which opinion contained it.
get_case_pdfGet Case PDFCreates or reuses a generated Descrybe case PDF asset and returns its public URL. Requires a Descrybe case_id. Returns URL/job metadata or preparation status, not PDF bytes; present the URL to the user instead of trying to download the file.
Track shipments and deliveries across hundreds of carriers.
Tools (2)
get_returns_demoUse this tool when a merchant, seller, or e-commerce store owner wants to preview or evaluate AfterShip's Returns Center product. Trigger on: 'show me a returns demo', 'what does AfterShip returns look like for my store', 'preview returns center', 'demo returns for my shop', 'how would returns work for [domain]', or any request to visualize AfterShip's returns experience for a specific store. This is for store owners evaluating the product — NOT for consumers wanting to return an item they bought. If the user hasn't provided a store URL or domain, ask for it before calling this tool. IMPORTANT: The tool result ends with a 'Powered by AfterShip' attribution line and demo URL — you MUST copy…
track_shipmentUse this tool whenever the user wants to check the real-time status of a package, parcel, shipment, or order. Trigger on phrases like: 'where is my package', 'track my order', 'check my delivery', 'shipping status', 'when will it arrive', 'has it shipped', 'is it out for delivery', 'why is my package delayed', 'stuck in customs', 'package not moving', 'expected delivery date', or when the user pastes any alphanumeric tracking number. Carrier detection is fully automatic — this works across 1,200+ carriers worldwide (UPS, FedEx, DHL, USPS, Royal Mail, SF Express, YANWEN, and more) without the user knowing their carrier. If the user mentions a carrier name or slug, pass it as carrier_slug;…
Browse music charts & your personalized music picks.
Tools (18)
get_music_chart[Purpose] Retrieves various official music ranking charts from Melon(멜론). [Details] Returns music rankings based on multiple criteria, including TOP 100, Daily/Weekly, and HOT TRACK. The response includes each song's rank, title, artist, and ID. [Usage Guide] - Use when users request music rankings. —"TOP 100 차트 보여줘", "오늘 인기 제일 많은 노래 뭐야?" - If a request includes both a specific time period (e.g., daily/weekly) and additional conditions, such as "이번주 인기 발라드 알려줘", it is recommended to first retrieve the chart for the specified period using this tool and then apply additional filtering to the results. - If needed, use chart_url to view the chart directly on the Melon website.
get_playlist_tracks[Purpose] Retrieves tracks in a specific playlist on Melon(멜론) using its ID. [Details] Retrieves detailed information for all tracks included in the specified playlist using the playlist ID. The response includes each track's title, artist, and ID. [Usage Guide] Use when users request the tracks in a specific playlist. —"이 플레이리스트에 있는 노래 목록 보여줘".
get_music_content_details[Purpose] Retrieves detailed information about songs, albums, and artists on Melon(멜론) using their IDs. [Details] Uses content IDs obtained from other tools (e.g., search, chart) to retrieve detailed information such as release date, genre, and description. The tool supports parallel processing for retrieving multiple IDs in a single request. For single-ID queries, the result is returned directly. For multiple-ID queries, results are returned grouped by each ID. [Usage Guide] - Single Retrieval: Use when detailed information for a specific content is required. —"이 앨범 소개글 보여줘", "이 가수 정보 알려줘" - Batch Retrieval: Use when querying information for multiple content items at once. —"이 앨범들의 발매일…
get_artist_contents[Purpose] Retrieves a list of tracks or albums for a specific artist from Melon(멜론). [Details] Retrieves specific artist's tracks or albums by using the artist ID, with filters based on participation type (all, featuring, lyricist/composer, etc.). If multiple versions of the same track (e.g., remix, live) exist, they are deduplicated and returned as a single entry. [Usage Guide] - Use when users request tracks by a specific artist —"아이유 노래 목록 보여줘", "박재범이 피처링한 노래 찾아줘". - Use when users request artist's album lists (discography) —"아이유 앨범 보여줘", "아이유 디스코그래피 알려줘". - To retrieve an artist's top/representative tracks, set the participation type as 'ALL' and sort by popularity. [Distinction]…
get_music_content_url[Purpose] Returns detail page URLs for content on Melon(멜론), such as songs, albums, or playlists. [Details] Generates and returns web URLs for viewing detailed information about content. [Usage Guide] Use when users request detailed information about specific content —"이 노래 정보 보여줘", "앨범 정보"— or when providing an additional link. Note that playlists returned in search results are DJ playlists. [Integration] Pass a content ID obtained from other tools (e.g., songId, albumId) to the content_id of this tool to generate a detail page URL, and include the URL in the response to the user.
get_genres[Purpose] Retrieves main genres and all their sub-genres on Melon(멜론) in a nested structure. [Details] Specify genre_code to retrieve information for the corresponding genre and its sub-genres only. If omitted, retrieves all available genres. Returns a mapping of genre codes to their descriptions and sub-genres. [Usage Guide] Use when users request genre information. Identify the most appropriate genre code from the returned list and use it as genre_code and sub_genre_code for `get_music_contents_by_genre` tool. [Integration] Use this tool in conjunction with `get_music_contents_by_genre`.
get_music_contents_by_genre[Purpose] Retrieves a list of songs, playlists, or classic albums belonging to a specific music genre on Melon(멜론). [Details] - 'songs': returns all songs classified under the genre, with optional sub-genre filtering. - 'popular_songs': returns the genre's hot tracks from Melon's official curated "Hot Tracks" playlist (operated by '장르HoTracks' DJ), reflecting the actual popularity ranking of the genre. - 'playlists': returns playlists featuring that genre. - 'masterpieces': returns classic/representative albums of that genre. [Usage Guide] - "댄스 장르 노래 들려줘", "발라드 곡 보여줘" → content_type="songs" - "인기 힙합곡 알려줘", "발라드 인기곡 추천해줘" → content_type="popular_songs" - "인디 음악 플레이리스트 찾아줘" →…
get_recently_played_music_contents[Purpose] Retrieves users' recently played songs or recently viewed playlists on Melon(멜론). [Details] Retrieves a list of 'recently played songs' or 'recently viewed playlists' based on the user's listening and viewing history. The API provides a fixed maximum of 100 items. The page/limit parameters only paginate within this fixed dataset. [Usage Guide] Use when users request their recent activity history. —"최근에 들은 노래 뭐야?", "아까 봤던 플레이리스트 다시 보고 싶어".
get_my_created_playlists[Purpose] Retrieves a list of playlists 'created by me' on Melon(멜론). [Details] Retrieves playlists the user has created and owns: standard playlists ('My Playlist'), DJ playlists ('My DJ Playlist'), and the full list of user-created playlists. [Usage Guide] Use when users request their own playlists. —"내가 만든 플레이리스트 보여줘", "내 플레이리스트 목록", "내 DJ 플레이리스트 찾아줘". [Distinction] `get_my_liked_music_contents` retrieves playlists that the user has liked, whereas this tool retrieves playlists the user has created.
get_my_most_listened_songs[Purpose] Retrieves the ranking of the user's most played songs over a specified period on Melon(멜론). [Details] - Retrieves a ranked list of the most played songs based on the user's listening statistics for one of the following periods: the last 1 week, 1 month, 3 months, a specific month (YYYYMM), or a specific date (YYYYMMDD). - Multiple periods can be queried in a single request. - A maximum of 100 songs can be retrieved per request. - term_list parameter supports both single-period and multiple-period queries. Response is returned directly for single-period queries, while for multiple-period queries, responses are returned grouped by each period. [Usage Guide] - Single Period: "내가 제일…
get_my_liked_music_contents[Purpose] Retrieves a list of all types of content the user has 'liked' on Melon(멜론). [Details] This tool provides comprehensive access to users' liked content across multiple categories. Retrieves all content types that the user has 'liked', including songs, albums, playlists (standard playlists, DJ playlists, artist playlists, or all playlists if unspecified), videos, genres, and tags. [Usage Guide] Use when users request content related to their likes. —"내가 좋아요 한 노래 목록 보여줘", "좋아요 누른 앨범들 찾아줘". [Distinction] `get_my_created_playlists` retrieves playlists created by the user, whereas this tool retrieves playlists that the user has 'liked'.
get_latest_music_contents[Purpose] Retrieves a list of newly released songs, albums, and videos on Melon(멜론), sorted by release date. [Details] Applies region filters (domestic/international) when retrieving a list of newly released content. [Usage Guide] Use when users request newly released content regardless of ranking. —"새로 나온 노래 뭐 있어?", "최신 앨범 목록 보여줘". [Distinction] 'NEWEST' type in `get_music_chart` returns a popularity ranking of new songs, whereas this tool provides a list sorted strictly by release date, regardless of popularity.
create_playback_url[Purpose] Generates a playback URL for given content (song, album, playlist, music video) on Melon(멜론). [Details] Generates and returns web URLs that allow users to play content directly. [Usage Guide] - Play songs: Pass a list of song_id values into the song_ids parameter. - Play playlists: Pass a list of playlist_seq values into the playlist_seqs parameter. - Play albums: Pass a list of album_id values into the album_ids parameter. - Play music video: Pass a single mv_id into the mv_id parameter. [Caution] - Use only one parameter at a time (either song_ids, playlist_seqs, album_ids, or mv_id). - This tool does not play content directly; it provides a playback URL that users can execute.
get_melon_curated_playlists[Purpose] Retrieves a list of official playlists curated and recommended by Melon(멜론). [Details] Retrieves playlists from Melon's official recommendation categories, such as 'Daily Pick', 'Today's Playlist', and 'Theme Recommendation'. [Usage Guide] Use when users request Melon's official recommendations. —"멜론 추천 플레이리스트", "오늘의 플레이리스트". [Distinction] If the user mentions contextual or mood-based keywords such as "driving" or "workout", use `search_melon_music_contents` tool instead of this tool. [Integration] Use the retrieved playlist IDs as input for the `create_playback_url` tool to enable direct playback.
search_melon_music_contents[Purpose] Searches for all types of content on Melon(멜론)—songs, albums, artists, videos, playlists—using keywords. [Details] Performs a unified search based on user-provided keywords, or narrows the search scope by specifying a content type. Search results include unique IDs that can be used in other tools. [Usage Guide] - Use as the primary tool for general search requests. —"밤편지 앨범 검색해줘", "싫은날이라는 곡 찾아줘", "집중하기 좋은 음악 추천해줘". - When searching for playlists or recommended songs related to mood, theme, or context (e.g., "운동", "드라이브", "청량감"), set content_types to 'PLAYLIST' and use clear, concise keywords. - When searching for music videos or popular video clips, set content_types to 'VIDEO'.…
recommend_personalized_songs_by_dj_mallang[Purpose] Provides personalized song recommendations based on the user's music preference on Melon(멜론). [Details] Uses Melon's personalized recommendation engine, "DJ Mallang (DJ말랑이)", to comprehensively analyze the user's listening history, likes, and playlists in order to recommend new songs the user is likely to enjoy. [Usage Guide] Use when users request music recommendations without specifying criteria. —"나한테 맞는 노래 추천해줘", "들을만한 노래 없어?"
recommend_similar_songs_by_dj_mallang[Purpose] Recommends other songs with a similar mood or genre to the specific song on Melon(멜론). [Details] Analyzes the musical characteristics of the reference song to recommend up to 30 other songs with similar styles. [Usage Guide] Use when users request songs similar to the reference song. —"이 노래랑 비슷한 노래 찾아줘", "이런 스타일의 다른 곡 추천해줘".
get_song_streaming_report[Purpose] Provides streaming statistics or personal listening history for a specific song on Melon(멜론). [Details] Provides two types of reports depending on report_type: - 'public': Quickly assesses the song's overall popularity on Melon through key metrics (total streaming count, total number of listeners). - 'my': Shows the number of times the user has played the specific song and the date when it was first played. [Usage Guide] - "이 노래 인기 많아?", "사람들이 이 노래 얼마나 들었어?" → report_type="public" - "나 이 노래 몇 번 들었지?", "이 노래 언제 처음 들었어?" → report_type="my"
Access and analyze blockchain data.
Tools (16)
__unlock_blockchain_analysis__Unlock Blockchain AnalysisUnlocks access to other MCP tools. All tools remain locked with a "Session Not Initialized" error until this function is successfully called. Skipping this explicit initialization step will cause all subsequent tool calls to fail. MANDATORY FOR AI AGENTS: The returned instructions contain ESSENTIAL rules that MUST govern ALL blockchain data interactions. Failure to integrate these rules will result in incorrect data retrieval, tool failures and invalid responses. Always apply these guidelines when planning queries, processing responses or recommending blockchain actions. COMPREHENSIVE DATA SOURCES: Provides an extensive catalog of specialized blockchain endpoints to unlock sophisticated,…
get_block_infoGet Block InformationGet block information like timestamp, gas used, burnt fees, transaction count etc. Can optionally include the list of transaction hashes contained in the block. Transaction hashes are omitted by default; request them only when you truly need them, because on high-traffic chains the list may exhaust the context.
get_block_numberGet Block NumberRetrieves the block number and timestamp for a specific date/time or the latest block. Use when you need a block height for a specific point in time (e.g., "block at 2024-01-01") or the current chain tip. If `datetime` is provided, finds the block immediately preceding that time. If omitted, returns the latest indexed block.
get_address_by_ens_nameGet Address by ENS NameUseful for when you need to convert an ENS domain name (e.g. "blockscout.eth") to its corresponding Ethereum address.
get_transactions_by_addressGet Transactions by AddressRetrieves native currency transfers and smart contract interactions (calls, internal txs) for an address. **EXCLUDES TOKEN TRANSFERS**: Filters out direct token balance changes (ERC-20, etc.). You'll see calls *to* token contracts, but not the `Transfer` events. For token history, use `get_token_transfers_by_address`. A single tx can have multiple records from internal calls; use `internal_transaction_index` for execution order. Requires an `age_from` date to scope results for performance and relevance. Use cases: - `get_transactions_by_address(address, age_from)` - get all txs to/from the address since a given date. - `get_transactions_by_address(address, age_from, age_to)` - get all txs…
get_token_transfers_by_addressGet Token Transfers by AddressGet ERC-20 token transfers for an address within a specific time range. Use cases: - `get_token_transfers_by_address(address, age_from)` - get all transfers of any ERC-20 token to/from the address since the given date up to the current time - `get_token_transfers_by_address(address, age_from, age_to)` - get all transfers of any ERC-20 token to/from the address between the given dates - `get_token_transfers_by_address(address, age_from, age_to, token)` - get all transfers of the given ERC-20 token to/from the address between the given dates **SUPPORTS PAGINATION**: If response includes 'pagination' field, use the provided next_call to get additional pages.
lookup_token_by_symbolLookup Token by SymbolSearch for token addresses by symbol or name. Returns multiple potential matches based on symbol or token name similarity. Only the first ``TOKEN_RESULTS_LIMIT`` matches from the Blockscout API are returned.
get_contract_abiGet Contract ABIGet smart contract ABI (Application Binary Interface). An ABI defines all functions, events, their parameters, and return types. The ABI is required to format function calls or interpret contract data.
inspect_contract_codeInspect Contract CodeInspects a verified contract's source code or metadata.
read_contractRead from ContractCalls a smart contract function (view/pure, or non-view/pure simulated via eth_call) and returns the decoded result. This tool provides a direct way to query the state of a smart contract. Example: To check the USDT balance of an address on Ethereum Mainnet, you would use the following arguments: { "tool_name": "read_contract", "params": { "chain_id": "1", "address": "0xdAC17F958D2ee523a2206206994597C13D831ec7", "abi": { "constant": true, "inputs": [{"name": "_owner", "type": "address"}], "name": "balanceOf", "outputs": [{"name": "balance", "type": "uint256"}], "payable": false, "stateMutability": "view", "type": "function" }, "function_name": "balanceOf", "args":…
get_address_infoGet Address InformationGet comprehensive information about an address, including: - Address existence check - Native token (ETH) balance (provided as is, without adjusting by decimals) - First transaction details (block number and timestamp) for age calculation - ENS name association (if any) - Contract status (whether the address is a contract, whether it is verified) - Proxy contract information (if applicable): determines if a smart contract is a proxy contract (which forwards calls to implementation contracts), including proxy type and implementation addresses - Token details (if the contract is a token): name, symbol, decimals, total supply, etc. Essential for address analysis, contract investigation, token…
get_tokens_by_addressGet Tokens by AddressGet comprehensive ERC20 token holdings for an address with enriched metadata and market data. Returns detailed token information including contract details (name, symbol, decimals), market metrics (exchange rate, market cap, volume), holders count, and actual balance (provided as is, without adjusting by decimals). Essential for portfolio analysis, wallet auditing, and DeFi position tracking. **SUPPORTS PAGINATION**: If response includes 'pagination' field, use the provided next_call to get additional pages.
nft_tokens_by_addressGet NFT Tokens by AddressRetrieve NFT tokens (ERC-721, ERC-404, ERC-1155) owned by an address, grouped by collection. Provides collection details (type, address, name, symbol, total supply, holder count) and individual token instance data (ID, name, description, external URL, metadata attributes). Essential for a detailed overview of an address's digital collectibles and their associated collection data. **SUPPORTS PAGINATION**: If response includes 'pagination' field, use the provided next_call to get additional pages.
get_transaction_infoGet Transaction InformationGet comprehensive transaction information. Unlike standard eth_getTransactionByHash, this tool returns enriched data including decoded input parameters, detailed token transfers with token metadata, transaction fee breakdown (priority fees, burnt fees) and categorized transaction types. By default, the raw transaction input is omitted if a decoded version is available to save context; request it with `include_raw_input=True` only when you truly need the raw hex data. Essential for transaction analysis, debugging smart contract interactions, tracking DeFi operations.
get_chains_listGet List of ChainsGet the list of known blockchain chains with their IDs. Useful for getting a chain ID when the chain name is known. This information can be used in other tools that require a chain ID to request information.
direct_api_callDirect Blockscout API CallCall a raw Blockscout API endpoint for advanced or chain-specific data. Do not include query strings in ``endpoint_path``; pass all query parameters via ``query_params`` to avoid double-encoding. **SUPPORTS PAGINATION**: If response includes 'pagination' field, use the provided next_call to get additional pages. Returns: ToolResponse[Any]: Must return ToolResponse[Any] (not ToolResponse[BaseModel]) because specialized handlers can return lists or other types that don't inherit from BaseModel. The dispatcher system supports flexible data structures.
Turn AI insights into documents.
Tools (3)
draw_svg_imageDraw Notes WidgetCreates custom vector graphics and illustrations from SVG code. Use for freeform drawings, icons, logos, custom shapes, artistic designs, precise geometric patterns, or when user needs pixel-perfect control over visual elements. "draw an image", "create an icon", "design a logo", "make a custom graphic", or needs specific visual styling not suited to standard diagrams. Choose this over Mermaid when the user wants artistic/custom graphics rather than structured diagrams. Supports an optional background object: choose a color (white by default; use black when the user asks for dark mode; yellow also supported) and a pattern (blank, dotted, or squared; defaults to dotted). Use only these…
generate_mermaid_diagramDraw Notes WidgetCreates visual diagrams from Mermaid syntax. Supports three diagram types: flowcharts (process flows, decision trees, workflows), mindmaps (hierarchical ideas, brainstorming, concept maps), and timelines (chronological events, project milestones, histories). "create a flowchart", "visualize the process", "show the workflow", "make a mindmap", "brainstorm ideas", "map concepts", "create a timeline", "show events over time", or describes structured visualization needs. Choose this over SVG when the user wants a structured diagram rather than freeform graphics. Supports an optional background object: choose a color (white by default; use black when the user asks for dark mode; yellow also…
create_markdown_text_documentMarkdown WidgetRender markdown content as beautifully formatted rich text in an interactive Goodnotes widget. Supports headings, lists, code blocks, tables, and more. Use this to present any text content the user wants to see formatted, save, or share. "show this as markdown", "format this text", "create a document", "save these notes", or any request involving structured text display.
Discover every grant opportunity in existence..
Tools (5)
search_grantsSearch GrantsSearch 84,000+ grant opportunities by keyword, state, source type, funder, and more. Uses semantic search (embeddings + full-text + scoring) combined with live AI-powered web discovery for comprehensive results. Returns active grants ranked by relevance with fit scores, deadlines, amounts, and application links. Use this as the starting point to find relevant grants.
get_grantGet Grant DetailsGet full details for a specific grant by its slug. Returns eligibility criteria, application link, deadline, amount, funder info, and tags. Use search_grants first to find valid slugs.
search_fundersSearch FundersSearch 133,000+ US foundations by name, state, NTEE code, asset range, and annual income range. Returns key metrics: name, state, total assets, annual income (from IRS 990), NTEE category, and mission. Use get_funder with the returned slug for full profiles including actual giving history.
get_funderGet Funder ProfileGet a full foundation profile including mission, 5-year financials, recent grants awarded, key officers, and application info. Accepts a foundation slug (from search_funders results) or EIN (e.g. '13-1684331').
get_past_winnersGet Past WinnersCompetitive intelligence: see who has won a specific federal grant program. Shows top recipients grouped by organization with award counts, total funding, and year-over-year trends. Filter by CFDA number, agency, program name, or state. Supports agency abbreviations: NIH, NSF, EPA, DOE, DOD, USDA, NASA, SBA, etc.
Lets you create and trade prediction markets on any question to forecast outcomes and aggregate beliefs.
Tools (5)
search-marketsSearch MarketsSearch for prediction markets with optional filters
get-marketGet MarketGet detailed information about a specific market
get-userGet UserGet user information by username
get-betsGet BetsGet bets from markets or for users with various filtering options
search-usersSearch UsersSearch for users by username or display name
Exa Web Search + Code Docs Search.
Tools (2)
web_search_exaSearch the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.
web_fetch_exaRead a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).
Calm board-defense guidance for licensed pros..
Tools (10)
get_board_guidanceGet general educational guidance for a licensed professional facing a state licensing board matter. Returns response-deadline guidance, jurisdictional context, and what to include/avoid. Not legal advice. Read-only; does not transmit user data.
get_response_letter_guidanceReturns a structured outline for a written response letter to a licensing board, including sections to include, tone guidance, and what to avoid. Read-only; does not draft the letter or transmit user data.
find_relevant_guideFind the most relevant BoardWise educational guide URL for a given topic, profession, or situation. If state and profession are provided, prioritizes the state + profession specific public SEO guide page when available. Returns up to 3 matching guides with titles and URLs. Read-only.
get_resourcesGet curated BoardWise resources for a specific situation type. Returns a list of relevant educational guides and tools (e.g. hearing prep simulator, CAP builder, early-termination workflow). Read-only.
get_boardwise_capabilitiesReturns a complete list of situations BoardWise can help with (board complaints, CEU audits, consent agreements, hearings, probation, self-reports, renewals, subpoenas, CDL matters, etc.) and the privacy + product features available (Zero Sensitive Data Retention, free intake, PDF/Word export, e-signature, optional notary, hearing practice simulator, board-specific rules engine, dynamic form filling). Read-only. Use when the user asks what BoardWise does, what it supports, or how it works.
get_ceu_audit_guidanceReturns profession- and state-specific guidance for responding to a CEU/CE audit notice. Includes overview, commonly requested documents, common mistakes, typical next steps, and links to relevant BoardWise resources. Retrieval-based; no LLM call. Read-only; does not transmit user data.
explain_notice_of_investigationExplains what a notice of investigation generally means for a licensed professional, what to review, common response considerations, and typical process progression. Calm and non-alarmist. Retrieval-based; no LLM call. Read-only.
identify_required_documentsReturns a structured list of documents commonly requested or reviewed for a given profession/state/issue. Framed as 'commonly requested', not legal advice. Retrieval-based; no LLM call. Read-only.
extract_deadlinesExtracts likely deadlines (response deadlines, hearing dates, submission dates, audit deadlines, compliance dates) from pasted notice text. Uses deterministic regex/keyword parsing — no LLM call by default. Returns each extracted date with kind, confidence, ISO date when parseable, and surrounding context. Read-only; text is processed in-memory and not stored.
explain_possible_next_stepsExplains common procedural next steps for a licensed professional facing a board matter, optionally branching on the current stage. Includes possible board actions, common timelines, and preparation suggestions. Retrieval-based; no LLM call. Supportive and realistic — avoids definitive legal predictions. Read-only.
Add authentication, organizations, and billing.
Tools (2)
clerk_sdk_snippetClerk SDK snippetGet Clerk SDK code snippets and patterns.
list_clerk_sdk_snippetsList Clerk SDK snippetsList all available Clerk SDK snippets and bundles. Filter by tag to find specific functionality.
Check links, phones, and emails for scams.
Tools (6)
reputation-check_linkCheck Link ReputationUse this when you need to check if a link or URL is safe, suspicious, or malicious. Provides reputation verdict based on threat intelligence database. Returns one of: - malicious: Confirmed harmful link - suspicious: Potentially dangerous link - safe: Verified safe link - unknown: No threat intelligence available Cross-tool workflow: - For unknown or suspicious verdicts, consider using reputation-whois to check domain registration details (age, registrar, abuse contact). - If the URL redirects to a different domain, consider scanning the destination URL separately. - If the URL came from an email or text message, consider checking the sender with reputation-check_email or…
reputation-check_phoneCheck Phone ReputationUse this when you need to check if a phone number is associated with scams or suspicious activity. Provides reputation verdict and additional phone information. Returns one of: - malicious: Confirmed scam or spam phone number - suspicious: Potentially dangerous number - safe: Verified legitimate number - unknown: No threat intelligence available Also provides optional details like carrier, location, and phone type when available. Cross-tool workflow: - If the caller provided links, consider scanning them with reputation-check_link. - If the caller provided email addresses, consider scanning them with reputation-check_email. Do not use this for phone number lookups, caller ID services, or…
reputation-check_emailCheck Email ReputationUse this when you need to check if an email address is associated with phishing, scams, or malicious activity. Checks the email domain against threat intelligence database. Returns one of: - malicious: Confirmed phishing or malicious email domain - suspicious: Potentially dangerous email domain - safe: Verified legitimate email domain - unknown: No threat intelligence available Cross-tool workflow: - If the email contains URLs, consider scanning them with reputation-check_link. - If the email contains phone numbers, consider scanning them with reputation-check_phone. - For unknown or suspicious verdicts, consider using reputation-whois to check domain registration details (age, registrar,…
reputation-reportReport Suspicious ContentUse this when a user wants to report a suspicious link, email address, or phone number. Submits the indicator to the threat intelligence system for analysis. Only use when explicitly requested by the user. Do not use this to automatically report every checked item.
reputation-whoisCheck Domain WHOIS InformationUse this when you need to look up domain registration information to verify legitimacy or identify suspicious patterns. Provides WHOIS/RDAP data including registrar, registration dates, name servers, and abuse contacts. Particularly useful for identifying newly registered domains (common in phishing and scams). Returns the registrar's abuse contact email when available, which can be used for filing complaints about fraudulent domains. Cross-tool workflow: - Consider using reputation-check_link to check the domain's threat reputation alongside WHOIS registration data. Do not use this for general domain availability checks or bulk domain searches.
reputation-scan_allScan All IndicatorsUse this when you need to check multiple links, emails, or phone numbers at once. Scans all indicators concurrently and returns a unified result. Each indicator needs: - type: 'url', 'email', or 'phone' - value: the URL, email address, or phone number (E.164 format for phones) Returns a summary with counts per verdict and individual results for each indicator. Prefer this over individual scan tools when 3 or more indicators are present. Maximum 10 indicators per request. Cross-tool workflow: - For unknown URL or email verdicts, consider using reputation-whois on the associated domains for additional registration context and abuse contact information.
Provides audited smart contract libraries for Cairo to build secure applications on StarkNet and other Cairo-based blockchains.
Tools (8)
cairo-erc20Make a fungible token per the ERC-20 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-erc721Make a non-fungible token per the ERC-721 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-erc1155Make a non-fungible token per the ERC-1155 standard. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-accountMake a custom smart contract that represents an account that can be deployed and interacted with other contracts, and can be extended to implement custom logic. An account is a special type of contract that is used to validate and execute transactions. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-multisigMake a multi-signature smart contract, requiring a quorum of registered signers to approve and collectively execute transactions. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-governorMake a contract to implement governance, such as for a DAO. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-vestingMake a vesting smart contract that manages the gradual release of ERC-20 tokens to a designated beneficiary based on a predefined vesting schedule. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
cairo-customMake a custom smart contract. Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.
Find your next hike.
Tools (5)
find_trails_near_locationFind trails near a locationFind hiking, running, biking, backpacking or other trails for outdoor activities near a set of coordinates within an optional specified maximum radius (meters). Use this tool when the user: * Requests trails near a specific point of interest or landmark. * Requests trails near a named location within a specified radius or accessible within a specified time constraint. * Provides specific latitude and longitude coordinates. For most named places, use the "search within bounding box" tool if possible. Use this tool as a fallback when the bounding box of the named place is unknown. Users can specify filters related to appropriate activities, attractions, suitability, and more. Numeric range…
find_trails_within_boundsFind trails within boundsFind hiking, running, biking, backpacking or other trails for outdoor activities within a specified bounding box defined by southwest and northeast coordinates. Use this tool when the user: * Requests trails within specific geographic boundaries or coordinates. * Requests trails near a named geographic or political place, such as a continent, country, state, province, region, city, town, or neighborhood and you know the bounding box for that place. * Requests trails within a national, state or local park or other protected area and you know the bounding box for that park. If the bounding box for the named place is not known, use the "find trails near a location" tool instead to find trails…
search_trails_by_nameSearch trails by nameSearch for hiking, running, biking, backpacking or other trails by full or partial name match. Use this tool when the user: * Requests a specific trail by name (e.g., "Avalanche Lake Trail", "Half Dome") * Searches for trails with specific keywords in the name The search can biased towards results near the provided coordinates if they are provided explicitly or available from the request metadata. If there is a clear match to the user's query, the model should automatically make a subsequent call to the `get_trail_details` tool to present the user with complete details for the matching trail. In the response, length and distance values are returned both in meters and imperial units. These…
get_trail_detailsShow trail detailsFind detailed information about a trail from AllTrails. Get descriptive overviews and specific accessibility information. Includes structured data about suitable activities, and feature highlights along the trail. Get stats about the trail geography and length, and stats about associated user-generated content. In the response, length and distance values are returned both in meters and imperial units. These MUST be displayed to the user in the units most appropriate for the user's locale, e.g. feet or miles for US English users. Recent reviews are summarized in the `review_summary` field. If the user wants information that might be found in specific reviews, direct the user to the AllTrails…
get_trail_weather_overviewGet trail's weather forecastGet 7-day forecast for a trail at its trailhead, including high/low temperatures. For more detailed weather information, including current conditions, sunrise/sunset times, and weather alerts, direct the user to the AllTrails web URL for the trail (available in the `get_trail_details` tool response).
Helps users search, compare, and book ferry tickets across routes and operators worldwide.
Tools (4)
get_portsGet PortsGet a list of global ports and their details
get_disruptionsGet DisruptionsGet a list of disruptions for a given date and country
get_direct_connections_for_portsGet Direct ConnectionsGet a list of all the direct connections between ports
search_tripsSearch TripsGet a list available ferry trips between two ports on a specific date
Allows users to discover, book, and purchase tickets for activities, tours, and experiences at attractions worldwide.
Tools (6)
experience_availabilityGet availability information for a specific experience including dates, times, and pricing
experience_detailsGet detailed information about a specific experience by ID
list_tagsList all category tags
render_activity_tilesRender activity tiles for a list of activity IDs, returning an embeddable widget URI
search_experiencesSearch for travel experiences with comprehensive filtering options. Returns available categories, tags, and regions with IDs for further filtering.
search_regionsSearch for regions by name
Find cheap flights, including hidden-city fares.
Tools (10)
sk_flights_searchSkiplagged Flights SearchSearch Skiplagged for flights between specific locations with filtering options for passengers, fare class, stops, airlines, and timing preferences
sk_destinations_anywhereSkiplagged Flexible Destination SearchFind cheapest destinations from a departure city when flexible about where to go. Perfect for discovering travel opportunities and deals.
sk_flex_departure_calendarSkiplagged One-Way Fare CalendarGenerate a flexible calendar of the lowest one-way fares around a chosen departure, returning date → cheapest-price entries to help pick the best day to fly. Intended for flexible-date price discovery, not exact itinerary selection.
sk_flex_return_calendarSkiplagged Round-Trip Price CalendarGenerate a flexible round-trip price calendar for a fixed-length stay around a chosen travel window. Returns (depart date, return date, lowest total price) entries for nearby date pairs that preserve the original trip length; intended for price discovery, not exact itinerary selection.
sk_hotels_searchSkiplagged Hotel SearchSearch Skiplagged for hotels in a city with specific check-in and check-out dates, including ratings and pricing.
sk_cars_searchSkiplagged Car SearchSearch Skiplagged for rental cars between pickup and dropoff locations/dates, returning prices, companies, and car details.
sk_hotel_detailsSkiplagged Hotel DetailsFetch room-level availability, pricing, and amenities for a specific hotel and stay dates.
sk_faq_searchSearch Skiplagged FAQSearch FAQ for relevant answers about Skiplagged - company, stuff, its products, and policies. Useful for customer support and general inquiries
sk_resolve_locationResolve location to airport codeResolve latitude and longitude to the IATA code of nearest airport and city information
sk_resolve_iataResolve city name to airport codeResolve a city name to a valid IATA code
Find your ideal hotel at the best price..
Tools (3)
trivago-accommodation-radius-searchSearch for accommodations and hotels using coordinates and radius on Trivago. Use this tool when you want to find accommodations near a specific location or street. The coordinates refer to the search target (e.g. a landmark, neighborhood, or address the user is asking about), NOT the user's personal location. Derive coordinates from the place or landmark mentioned in the user's query. Additional Information: { "knownInformation": { "currentYear": "2026", "today": "2026-06-08" } }
trivago-accommodation-searchSearch for accommodations and hotels on Trivago. Use this tool when you want to find accommodations in broader areas like cities, countries, etc. If you are interested in a specific location, use the trivago-accommodation-radius-search tool. Additional Information: { "knownInformation": { "currentYear": "2026", "today": "2026-06-08" } }
trivago-search-suggestionsSuggestions are used to provide a list of possible search terms based on the user's query. Query can be city, country. You must pick output that are close to the user query. Example: Input: Query: "Berlin" Query: "Germany"
Book travel experiences around the world.
Tools (2)
get_experience_detailsGet experience detailsRetrieves enriched information for a specific Viator experience, including detailed descriptions, highlights, imagery, pricing, and the click-out URL.The model should call this tool only when the user clearly refers to a specific experience—either by selecting it in the UI or by asking follow-up questions such as “Tell me more about…”;if multiple experiences were shown, the model must resolve ambiguity by asking which one the user means. This tool is intended for deepening experience understanding rather than search, and should only be invoked with a code previously returned by search_experiences.
search_experiencesSearch for experiencesRetrieves a curated list of Viator experiences based on a free-text search of what the user wants (destination, activity type, and preferences), plus trip dates and optional refiners (budget, duration, etc.). The model must supply searchTerm as natural language describing where and what the user is looking for (e.g. "walking tours in Paris, France", "kid friendly food experiences in Rome"). Dates, prices, duration limits, and currency belong in their dedicated parameters—not inside searchTerm. Prefer searchTerm as natural language for the partner free-text search. If searchTerm is omitted or blank, the query is built by concatenating deprecated location and category as-is (natural language)…