MCP.so
Sign In

Tavily McpFeatured

@tavily-ai

Repository

About Tavily Mcp

Production ready MCP server with real-time search, extract, map & crawl.

#tavily#web-crawler#data-extraction

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "tavily-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ],
      "env": {
        "TAVILY_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Tools

5

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

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

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

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

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.

Overview

What is Tavily MCP?

Tavily MCP is a Model Context Protocol server that provides real-time web search, intelligent data extraction, web mapping, and web crawling tools. It integrates with MCP clients such as Claude Code and Cursor, and is designed for developers who need web-powered capabilities in their AI agent workflows.

How to use Tavily MCP?

You can run Tavily MCP locally using npx -y tavily-mcp@latest, or connect to a remote MCP server at https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>. Set your Tavily API key via the TAVILY_API_KEY environment variable or pass it in the remote URL. Optionally configure default parameters for the tavily-search tool using the DEFAULT_PARAMETERS environment variable.

Key features of Tavily MCP

  • Real-time web search via the tavily-search tool
  • Intelligent data extraction from web pages via tavily-extract
  • Web mapping tool that creates structured website maps
  • Web crawler for systematic website exploration

Use cases of Tavily MCP

  • Building knowledge graphs by combining Tavily MCP with Neo4j MCP
  • Integrating web search and data extraction into coding assistants (Cline in VS Code)
  • Real-time web research for AI agents and chat assistants
  • Extracting and structuring data from multiple web pages for analytics

FAQ from Tavily MCP

What does Tavily MCP do?

Tavily MCP provides search, extract, map, and crawl tools that give AI applications real-time access to web content and structure.

What are the prerequisites to use Tavily MCP?

You need a Tavily API key (get one at tavily.com), a compatible MCP client (Claude Desktop or Cursor), Node.js v20 or higher, and optionally Git for the local installation.

How do I run Tavily MCP locally?

Run npx -y tavily-mcp@latest with the TAVILY_API_KEY environment variable set. For a full configuration, add the command to your client’s MCP settings file.

How do I connect to the remote Tavily MCP server?

Use the URL https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key> with a remote MCP client like Claude Code or Cursor. You can also authenticate via OAuth instead of providing an API key in the URL.

Can I set default parameters for search requests?

Yes, set the DEFAULT_PARAMETERS environment variable to a JSON object (e.g., {"include_images": true, "max_results": 15}) to apply defaults to all tavily-search calls.

Frequently asked questions

What does Tavily MCP do?

Tavily MCP provides search, extract, map, and crawl tools that give AI applications real-time access to web content and structure.

What are the prerequisites to use Tavily MCP?

You need a Tavily API key (get one at tavily.com), a compatible MCP client (Claude Desktop or Cursor), Node.js v20 or higher, and optionally Git for the local installation.

How do I run Tavily MCP locally?

Run `npx -y tavily-mcp@latest` with the `TAVILY_API_KEY` environment variable set. For a full configuration, add the command to your client’s MCP settings file.

How do I connect to the remote Tavily MCP server?

Use the URL `https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>` with a remote MCP client like Claude Code or Cursor. You can also authenticate via OAuth instead of providing an API key in the URL.

Can I set default parameters for search requests?

Yes, set the `DEFAULT_PARAMETERS` environment variable to a JSON object (e.g., `{"include_images": true, "max_results": 15}`) to apply defaults to all `tavily-search` calls.

Comments

Basic information

Category

Search

License

MIT

Transports

stdio

Author

tavily-ai

Submitted by

mmnxc9785 mafxx9785

More Search MCP servers

Version 2.0 is here!!

mixelpixx

MCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites

249

Google News MCP Server

ChanMeng666

【Star-crossed coders unite!⭐️】Model Context Protocol (MCP) server implementation providing Google News search capabilities via SerpAPI, with automatic news categorization and multi-language support.

124

Brave Search MCP Server

mikechao

An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities

121

Kagi MCP server

kagisearch

The Official Model Context Protocol (MCP) server for Kagi Search & other tools.

435

小红书自动搜索评论工具（MCP Server 2.0）

chenningling

这是一款基于 Playwright 开发的小红书自动搜索和评论工具，作为 MCP Server，可通过特定配置接入 MCP Client（如Claude for Desktop），帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。

436