Tavily Search MCP
Real-time web search and content extraction for AI
npx -y tavily-mcp{
"mcpServers": {
"tavily": {
"command": "npx",
"args": ["-y", "tavily-mcp"],
"env": { "TAVILY_API_KEY": "<YOUR_API_KEY>" }
}
}
}Tavily Search MCP is an officially maintained MCP server in the APIs & Integrations category, developed by Tavily. It runs locally on your machine, keeping your data private and giving you full control over the connection. It bridges the gap between Claude and your existing services without any custom integration code.
About Tavily Search MCP
Tavily MCP server provides AI assistants with real-time web search and content extraction optimised for research.
Features
- Real-time web search with answer synthesis
- Deep content extraction from URLs
- News and topic monitoring
- Domain filtering and result ranking
- Context-aware search results
- Rate-limited free tier available
Who Should Use Tavily Search MCP?
- 1Search and retrieve information using natural language
- 2Control a browser and scrape the web through Claude
- 3Connect Claude to third-party APIs without writing glue code
- 4Automate workflows that span multiple services and platforms
How to Install Tavily Search MCP
Before you start
You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.
- 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
- 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
- 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.
The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.