{"type":"mcp_server","name":"tavily-mcp","description":"The Tavily MCP server enables AI systems to interact with data sources and tools using the Model Context Protocol, providing real-time web search and data extraction capabilities through Tavily's search","category":"AI","language":"JavaScript","stars":2155,"forks":21,"owner":"tavily-ai","github_url":"https://github.com/tavily-ai/tavily-mcp","homepage":null,"setup":"## Setup\n\nBefore you begin, ensure you have:\n\n- [Tavily API key](https://app.tavily.com/home)\n  - If you don't have a Tavily API key, you can sign up for a free account [here](https://app.tavily.com/home)\n- [Claude Desktop](https://claude.ai/download) or [Cursor](https://cursor.sh)\n- [Node.js](https://nodejs.org/) (v20 or higher)\n  - You can verify your Node.js installation by running:\n    - `node --version`\n- [Git](https://git-scm.com/downloads) installed (only needed if using Git installation method)\n  - On macOS: `brew install git`\n  - On Linux: \n    - Debian/Ubuntu: `sudo apt install git`\n    - RedHat/CentOS: `sudo yum install git`\n  - On Windows: Download [Git for Windows](https://git-scm.com/download/win)\n\n### Running with NPX \n\n```bash\nnpx -y tavily-mcp@0.1.4  \n```\n\n### Installing via Smithery\n\nTo install Tavily MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@tavily-ai/tavily-mcp):\n\n```bash\nnpx -y @smithery/cli install @tavily-ai/tavily-mcp --client claude\n```\n\nAlthough you can launch a server on its own, it's not particularly helpful in isolation; instead, you should integrate it into an MCP client.\n\n### Configuring Cline\n\n1.  Open Cline in VS Code\n2.  Click on the Cline icon in the sidebar\n3.  Navigate to the \"MCP Servers\" tab ( 4 squares )\n4.  Search \"Tavily\" and click \"install\"\n5.  When prompted, enter your Tavily API key\n\nAlternatively, you can manually set up the Tavily MCP server in Cline by modifying the `cline_mcp_settings.json` file and adding the Tavily server configuration with your API key.\n\n### Configuring Cursor\n\n1.  Open Cursor Settings\n2.  Navigate to Features > MCP Servers\n3.  Click on the \"+ Add New MCP Server\" button\n4.  Fill out the information with the command `env TAVILY_API_KEY=your-api-key npx -y tavily-mcp@0.1.4` (replacing `your-api-key` with your actual API key).\n\n### Configuring the Claude Desktop app\n\nModify the `claude_desktop_config.json` file by adding the Tavily server configuration with your API key.\n\n### Git Installation\n\n1.  Clone the repository: `git clone https://github.com/tavily-ai/tavily-mcp.git`\n2.  Install dependencies: `npm install`\n3.  Build the project: `npm run build`\n\nFollow the configuration steps outlined in the [Configuring the Claude Desktop app](#configuring-the-claude-desktop-app-️) section above, using the below JSON configuration.\n","tools":"## Available Tools\n\n1.  Seamless interaction with the tavily-search and tavily-extract tools (allows interaction with Tavily's search and extraction capabilities).\n2.  Real-time web search capabilities through the tavily-search tool (provides access to real-time web search).\n3.  Intelligent data extraction from web pages via the tavily-extract tool (enables extraction of data from web pages).\n","faq":null,"created_at":"2025-01-27T16:56:37+00:00","updated_at":"2025-03-28T20:38:42+00:00","source_url":"https://model-context-protocol.com/servers/tavily-ai-model-context-protocol-server","related_articles":[]}