drio
Open app

tavily-server MCP Server

Source

Tavily MCP Server for Cline

Catalog onlyCatalog onlySTDIO

Overview

Tavily MCP Server is an AI-powered search server that utilizes the Tavily API and Model Context Protocol (MCP) to enhance the search capabilities of AI assistants, allowing them to perform detailed, up-to-date web searches and retrieve relevant information.

To use Tavily MCP Server, clone the repository, install the dependencies, configure your MCP client with the Tavily API key, and start the server. You can then call the search tool with your desired query.

  • AI-driven search functionality - Supports various search depths (basic and advanced) - Provides rich searching results with context snippets - AI-generated summaries for search results - Maintains a comprehensive search history with caching - Configurable for multiple MCP clients
  1. Enhancing AI assistants with real-time search capabilities
  2. Conducting research by retrieving recent data from the web
  3. Improving user interaction through AI-generated summaries

Add to your AI client

Use these steps to connect tavily-server 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-server-zenturacp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-server-zenturacp"
      ]
    }
  }
}

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-server-zenturacp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-server-zenturacp"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

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

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-server-zenturacp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-tavily-server-zenturacp"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

What is the prerequisite to run the server?

Node.js (v16 or higher) and an API key from Tavily are required.

Is Tavily MCP Server suitable for any MCP client?

Yes! It can be configured to work with various MCP clients like Cline and Claude Desktop.

How does the server handle errors?

The server provides detailed error messages for issues such as invalid API keys, network errors, and other common problems.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":411,"uuid":"a2944b06-89ed-4d39-ae47-7d567014d0d5","name":"tavily-server","title":"tavily-server MCP Server","description":"Tavily MCP Server for Cline","avatar_url":"https://avatars.githubusercontent.com/u/37262317?v=4","created_at":"2024-12-15T06:47:00.552Z","updated_at":"2024-12-16T06:52:36.556Z","status":"created","author_name":"zenturacp","author_avatar_url":"https://avatars.githubusercontent.com/u/37262317?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/zenturacp/tavily-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data