Official Tavily MCP server for AI search and content extraction, giving MCP clients web search, crawl, and extract tools.
Tavily exposes its functionality to MCP clients through the tavily mcp server. Official Tavily MCP server for AI search and content extraction, giving MCP clients web search, crawl, and extract tools.
The Tavily MCP server provides: - search, extract, map, crawl tools - Real-time web search capabilities through the tavily-search tool - Intelligent data extraction from web pages via the tavily-extract tool - Powerful web mapping tool that creates a structured map of website - Web crawler that systematically explores websites
The server is distributed via npm as mcp-remote, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply 3 environment variables: TAVILY_API_KEY, DEFAULT_PARAMETERS, TAVILY_HUMAN_ID. Keep credentials in your client's env block or a secrets manager rather than committing them.
Before you begin, ensure you have: - Tavily API key - If you don't have a Tavily API key, you can sign up for a free account here - Claude Desktop or Cursor - Node.js (v20 or higher) - You can verify your Node.js installation by running: - node --version -
### Example usage from Client
```json
{
"mcpServers": {
"tavily-mcp": {
"command": "npx",
"args": ["-y", "tavily-mcp@latest"],
"env": {
"TAVILY_API_KEY": "your-api-key-here",
"DEFAULT_PARAMETERS": "{\"include_images\": true, \"max_results\": 15, \"search_depth\": \"advanced\"}"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
Before you begin, ensure you have: - Tavily API key - If you don't have a Tavily API key, you can sign up for a free account here - Claude Desktop or Cursor - Node.js (v20 or higher) - You can verify your Node.js installation by running: - node --version -
| Variable | Description | Required |
|---|---|---|
| TAVILY_API_KEY | Credential the server authenticates with. | Yes |
| DEFAULT_PARAMETERS | Configuration value read at startup. | Optional |
| TAVILY_HUMAN_ID | Configuration value read at startup. | Optional |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.