tavily-ai/tavily-mcp

4.6

browser_automation ai_chatbot knowledge_and_memory

tavily-mcp is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.

If you are the rightful owner of tavily-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The Tavily MCP server is a Model Context Protocol server that integrates with AI systems to provide real-time web search and data extraction capabilities.

Try tavily-mcp with chat:

Tools

Functions exposed to the LLM to take actions

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.

tavily_extract

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

tavily_crawl

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

tavily_map

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

tavily_research

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.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources

Author

tavily-ai

Claim Ownership

Verify you have write access to the repository

Repository

https://github.com/tavily-ai/tavily-mcp

GitHub Stars

1,339

X (formerly Twitter)

https://x.com/tavilyai

License

MIT License

Last publish date

2025-01-27

Last update date

2026-03-10

Server configs

via npx in vs code

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "tavily_api_key",
        "description": "Tavily API Key",
        "password": true
      }
    ],
    "servers": {
      "tavily": {
        "command": "npx",
        "args": ["-y", "tavily-mcp@latest"],
        "env": {
          "TAVILY_API_KEY": "${input:tavily_api_key}"
        }
      }
    }
  }
}

via npx in cline

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

via npx in cursor

bash
env TAVILY_API_KEY=your-api-key npx -y tavily-mcp@latest

via npx in claude desktop

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

in claude desktop

{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": ["/path/to/tavily-mcp/build/index.js"],
      "env": {
        "TAVILY_API_KEY": "your-api-key-here"
      }
    }
  }
}

Top Comments

Related MCP Servers

View all browser_automation servers →

fetch-mcp

4.7

by zcaceres

This MCP server provides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown.

tavily-ai/tavily-mcp

Try tavily-mcp with chat:

Tools

tavily_search

tavily_extract

tavily_crawl

tavily_map

tavily_research

Prompts

No prompts

Resources

No resources

Related MCP Servers

fetch-mcp

markdownify-mcp

brightdata-mcp

fetcher-mcp

mcp-local-rag

Fetch

mcp

duckduckgo-mcp-server

mcp-crawl4ai-rag

mcp-server-serper

mobile-mcp

mcp-server

web-eval-agent

cursor-talk-to-figma-mcp

Notte Browser

Redbook-Search-Comment-MCP2.0

mcp-server-rag-web-browser

browser-control-mcp

comfyui-mcp-server

crawl4ai-mcp-server

ultimate_mcp_server

xhs-mcp-server

browser-mcp

bing-search-mcp

perplexity-mcp-zerver

perplexity-mcp-server

bing-cn-mcp-server