drio
Open app

Tavily Search MCP Server

Source

An MCP server implementation that integrates the Tavily Search API, providing optimized search capabilities for LLMs.

Catalog onlyCatalog onlySTDIO

Overview

Tavily Search MCP Server is an implementation that integrates the Tavily Search API, providing optimized search capabilities specifically designed for Large Language Models (LLMs).

To use the Tavily Search MCP Server, you need to clone the repository, install the necessary dependencies, and configure it with your Tavily API key. You can run the server using Node.js or Docker.

  • Web Search: Perform optimized web searches for LLMs with customizable parameters. - Content Extraction: Extracts relevant content from search results for better quality and size. - Optional Features: Include images, descriptions, and LLM-generated answers in the results. - Domain Filtering: Control which domains to include or exclude in search results.
  1. Enhancing search capabilities for AI-driven applications.
  2. Providing tailored search results for specific topics or domains.
  3. Integrating with other LLMs to improve information retrieval.

Add to your AI client

Use these steps to connect Tavily Search MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "tavily-search-mcp-server-apappascs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "tavily-search-mcp-server-apappascs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "tavily-search-mcp-server-apappascs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "tavily-search-mcp-server-apappascs": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "tavily-search-mcp-server-apappascs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "tavily-search-mcp-server-apappascs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-search-mcp-server-apappascs"
      ]
    }
  }
}

FAQ

Can I use Tavily Search MCP Server without an API key?

No, you need a Tavily API key to access the search functionalities.

Is there a free tier available for the Tavily API?

Yes, Tavily offers a free tier for users to get started.

How do I run the server using Docker?

You can build and run the Docker container using the provided commands in the setup guide.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":862,"uuid":"eb3c084f-8b01-4d34-a52c-de2c77526287","name":"tavily-search-mcp-server","title":"Tavily Search MCP Server","description":"An MCP server implementation that integrates the Tavily Search API, providing optimized search capabilities for LLMs.","avatar_url":"https://avatars.githubusercontent.com/u/6052803?v=4","created_at":"2025-01-28T02:15:14.351Z","updated_at":"2025-02-23T07:13:15.676Z","status":"created","author_name":"apappascs","author_avatar_url":"https://avatars.githubusercontent.com/u/6052803?v=4","tags":"tavily,search,mcp,server,llm,api","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/apappascs/tavily-search-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/ca718bca000ebcd574da131999a17aeff8c0eb1bfde3f980e328c88538899da0/68747470733a2f2f736d6974686572792e61692f62616467652f406170617070617363732f746176696c792d7365617263682d6d63702d736572766572","type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data