Tavily Mcp

tavily-ai/tavily-mcpOfficial

The Tavily MCP server provides real-time web search, intelligent data extraction, website mapping, and web crawling capabilities through four specialized tools: tavily-search for live web queries, tavily-extract for pulling structured data from pages, tavily-map for creating website maps, and a web crawler for systematic site exploration. It solves the problem of giving AI assistants direct access to current web information and the ability to analyze web content programmatically. The server can be deployed locally or accessed via Tavily's remote MCP endpoint, integrating with Claude and other MCP-compatible tools through API key or OAuth authentication.

GitHub stars: 2.1K
tools: 5
auth: Secret needed
transport: STDIO
env vars: 2
last updated: Jan 26, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp tavily-mcp --name tavily-mcp --env 'TAVILY_API_KEY=${TAVILY_API_KEY}'

Run in your terminal. add-mcp asks which agents to add it to, then asks for each value it needs. Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add tavily-mcp --env TAVILY_API_KEY=YOUR_TAVILY_API_KEY --env DEFAULT_PARAMETERS=YOUR_DEFAULT_PARAMETERS -- npx -y tavily-mcp

Run in your terminal. Replace YOUR_* placeholders with real values; add --scope user to install for every project.

Tools

Verified live · 5 tools

Verified live against the running server on Jun 11, 2026.

tavily_searchSearch the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.15 params

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

Parameters* required

countrystring

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 topi...default:

end_datestring

Will return all results before the specified end date. Required to be written in the format YYYY-MM-DDdefault:

exact_matchboolean

Only return results containing the exact phrase(s) in quotes in your query

exclude_domainsarray

List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site

include_domainsarray

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_faviconboolean

Whether to include the favicon URL for each resultdefault: false

include_image_descriptionsboolean

Include a list of query-related images and their descriptions in the responsedefault: false

include_imagesboolean

Include a list of query-related images in the responsedefault: false

include_raw_contentboolean

Include the cleaned and parsed HTML content of each search resultdefault: false

max_resultsnumber

The maximum number of search results to returndefault: 5

query*string

Search query

search_depthstring

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 elseone of basic · advanced · fast · ultra-fastdefault: basic

start_datestring

Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.default:

time_rangestring

The time range back from the current date to include in the search resultsone of day · week · month · year

topicstring

The category of the search. This will determine which of our agents will be used for the searchone of generaldefault: general

tavily_extractExtract content from URLs. Returns raw page content in markdown or text format.6 params

Extract content from URLs. Returns raw page content in markdown or text format.

Parameters* required

extract_depthstring

Use 'advanced' for LinkedIn, protected sites, or tables/embedded contentone of basic · advanceddefault: basic

formatstring

Output formatone of markdown · textdefault: markdown

include_faviconboolean

Include favicon URLsdefault: false

include_imagesboolean

Include images from pagesdefault: false

querystring

Query to rerank content chunks by relevance

urls*array

List of URLs to extract content from

tavily_crawlCrawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.11 params

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

Parameters* required

allow_externalboolean

Whether to return external links in the final responsedefault: true

extract_depthstring

Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latencyone of basic · advanceddefault: basic

formatstring

The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.one of markdown · textdefault: markdown

include_faviconboolean

Whether to include the favicon URL for each resultdefault: false

instructionsstring

Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.

limitinteger

Total number of links the crawler will process before stoppingdefault: 50

max_breadthinteger

Max number of links to follow per level of the tree (i.e., per page)default: 20

max_depthinteger

Max depth of the crawl. Defines how far from the base URL the crawler can explore.default: 1

select_domainsarray

Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)

select_pathsarray

Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)

url*string

The root URL to begin the crawl

tavily_mapMap a website's structure. Returns a list of URLs found starting from the base URL.8 params

Map a website's structure. Returns a list of URLs found starting from the base URL.

Parameters* required

allow_externalboolean

Whether to return external links in the final responsedefault: true

instructionsstring

Natural language instructions for the crawler

limitinteger

Total number of links the crawler will process before stoppingdefault: 50

max_breadthinteger

Max number of links to follow per level of the tree (i.e., per page)default: 20

max_depthinteger

Max depth of the mapping. Defines how far from the base URL the crawler can exploredefault: 1

select_domainsarray

Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)

select_pathsarray

Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)

url*string

The root URL to begin the mapping

tavily_researchPerform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.2 params

Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.

Parameters* required

input*string

A comprehensive description of the research task

modelstring

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. 'auto' automatically selects the best model.one of mini · pro · autodefault: auto

Configuration

TAVILY_API_KEY*secret

Your Tavily API key from tavily.com

DEFAULT_PARAMETERS

JSON string with default search parameters (e.g., {"include_images": true, "max_results": 15})

Readme

Tavily MCP Server

npm

The Tavily MCP server provides:

search, extract, map, crawl tools
Real-time web search capabilities through the tavily-search tool
Intelligent data extraction from web pages via the tavily-extract tool
Powerful web mapping tool that creates a structured map of website
Web crawler that systematically explores websites

📚 Helpful Resources

Tutorial on combining Tavily MCP with Neo4j MCP server
Tutorial on integrating Tavily MCP with Cline in VS Code

Remote MCP Server

Connect directly to Tavily's remote MCP server instead of running it locally. This provides a seamless experience without requiring local installation or configuration.

View the full README on GitHub

Details

Repository: github.com/tavily-ai/tavily-mcp
Category: Search & Web Crawling
Package: tavily-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active
Tools verified: Jun 11, 2026

Related Search & Web Crawling MCP servers

View all

DuckDuckGonickclyde/duckduckgo-mcp-serverProvides web search and content extraction via DuckDuckGo, with rate limiting, error handling, and LLM‑friendly output.1.1Kstars

One Search Mcpyokingma/one-search-mcpWeb search, URL discovery, scraping & extraction with agent-browser and search providers148stars

Searxng Mcpaicrafted/searxng-mcpMCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol7stars

AgentScrapehshintelligence/agent-scrapePay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.1stars

Code Indexachreftlili/code-indexSQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.0stars

Tavily MCP Serverseey215/tavily-mcpMCP server for advanced web search using Tavily API.0stars