> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Tavily MCP

> AI-powered search API for real-time web search, extraction, and crawling optimized for AI agents.

![Tavily MCP logo](https://mintcdn.com/composio-preview/IA0_SoMcsWt17HEC/images/toolkits/tavily_mcp.svg?fit=max\&auto=format\&n=IA0_SoMcsWt17HEC\&q=85\&s=42af1be113acd9481c0cefe94c5363d4)

* **Category:** model context protocol
* **Auth:** DCR\_OAUTH
* **Composio-managed OAuth available?** No
* **Tools:** 5
* **Triggers:** 0
* **Slug:** `TAVILY_MCP`
* **Version:** 20261018\_00

## Tools

> [accordion] Tavily crawl
>
> **Slug:** `TAVILY_MCP_TAVILY_CRAWL`
>
> Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The root URL to begin the crawl
>
> **limit** `integer`
>
> Total number of links the crawler will process before stopping
>
> **format** `string ("markdown" | "text")`
>
> The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.
>
> **max\_depth** `integer`
>
> Max depth of the crawl. Defines how far from the base URL the crawler can explore.
>
> **max\_breadth** `integer`
>
> Max number of links to follow per level of the tree (i.e., per page)
>
> **instructions** `string`
>
> Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.
>
> **select\_paths** `array`
>
> Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
>
> **extract\_depth** `string ("basic" | "advanced")`
>
> Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency
>
> **allow\_external** `boolean`
>
> Whether to return external links in the final response
>
> **select\_domains** `array`
>
> Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs.example.com\$)
>
> **include\_favicon** `boolean`
>
> Whether to include the favicon URL for each result

> [accordion] Tavily extract
>
> **Slug:** `TAVILY_MCP_TAVILY_EXTRACT`
>
> Extract content from URLs. Returns raw page content in markdown or text format.
>
> #### Input Parameters
>
> **urls** `array` *required*
>
> List of URLs to extract content from
>
> **query** `string`
>
> Query to rerank content chunks by relevance
>
> **format** `string ("markdown" | "text")`
>
> Output format
>
> **extract\_depth** `string ("basic" | "advanced")`
>
> Use 'advanced' for LinkedIn, protected sites, or tables/embedded content
>
> **include\_images** `boolean`
>
> Include images from pages
>
> **include\_favicon** `boolean`
>
> Include favicon URLs

> [accordion] Tavily map
>
> **Slug:** `TAVILY_MCP_TAVILY_MAP`
>
> Map a website's structure. Returns a list of URLs found starting from the base URL.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The root URL to begin the mapping
>
> **limit** `integer`
>
> Total number of links the crawler will process before stopping
>
> **max\_depth** `integer`
>
> Max depth of the mapping. Defines how far from the base URL the crawler can explore
>
> **max\_breadth** `integer`
>
> Max number of links to follow per level of the tree (i.e., per page)
>
> **instructions** `string`
>
> Natural language instructions for the crawler
>
> **select\_paths** `array`
>
> Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
>
> **allow\_external** `boolean`
>
> Whether to return external links in the final response
>
> **select\_domains** `array`
>
> Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs.example.com\$)

> [accordion] Tavily research
>
> **Slug:** `TAVILY_MCP_TAVILY_RESEARCH`
>
> Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.
>
> #### Input Parameters
>
> **input** `string` *required*
>
> A comprehensive description of the research task
>
> **model** `string ("mini" | "pro" | "auto")`
>
> Defines the degree of depth of the research. 'mini' is good for narrow tasks with few subtopics. 'pro' is good for broad tasks with many subtopics

> [accordion] Tavily search
>
> **Slug:** `TAVILY_MCP_TAVILY_SEARCH`
>
> Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Search query
>
> **topic** `string`
>
> The category of the search. This will determine which of our agents will be used for the search
>
> **country** `string`
>
> Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See [https://docs.tavily.com/documentation/api-reference/search](https://docs.tavily.com/documentation/api-reference/search) for the full list of supported countries.
>
> **end\_date** `string`
>
> Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD
>
> **start\_date** `string`
>
> Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.
>
> **time\_range** `string`
>
> The time range back from the current date to include in the search results
>
> **exact\_match** `string`
>
> Only return results containing the exact phrase(s) in quotes in your query
>
> **max\_results** `integer`
>
> The maximum number of search results to return
>
> **search\_depth** `string ("basic" | "advanced" | "fast" | "ultra-fast")`
>
> The depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else
>
> **include\_images** `boolean`
>
> Include a list of query-related images in the response
>
> **exclude\_domains** `array`
>
> List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site
>
> **include\_domains** `array`
>
> A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site
>
> **include\_favicon** `boolean`
>
> Whether to include the favicon URL for each result
>
> **include\_raw\_content** `boolean`
>
> Include the cleaned and parsed HTML content of each search result
>
> **include\_image\_descriptions** `boolean`
>
> Include a list of query-related images and their descriptions in the response
