
Tavily MCP Server
Connects Claude to Tavily's search and data extraction APIs through four main tools: search for real-time web queries, extract for pulling structured data from pages, map for creating site hierarchies, and crawl for systematic website exploration. You'll reach for this when you need Claude to look up current information, gather content from multiple sources, or build knowledge bases from web data. Works through the Tavily API, so you'll need an API key. The search tool supports domain filtering and search depth options, while extract handles batches of URLs. Ships as an npm package and runs via npx, so setup is straightforward in Claude Desktop, Cursor, or VS Code with Cline.
- tools
- 2
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Oct 31, 2025
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
tavily-searchReal-time web search capabilities through the tavily-search tool
Real-time web search capabilities through the tavily-search tool
No parameter schema in public metadata yet.
tavily-extractIntelligent data extraction from web pages via the tavily-extract tool
Intelligent data extraction from web pages via the tavily-extract tool
No parameter schema in public metadata yet.
Sponsors
Configuration
TAVILY_API_KEY*secretYour TAVILY_API_KEY
Readme
Tavily Crawl Beta
MCP demo
The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.
Developed by Anthropic, the Model Context Protocol (MCP) enables AI assistants like Claude to seamlessly integrate with Tavily's advanced search and data extraction capabilities. This integration provides AI models with real-time access to web information, complete with sophisticated filtering options and domain-specific search features.
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
Details
- Repository
- github.com/seey215/tavily-mcp
- Category
- Search & Web Crawling
- Package
@toolsdk.ai/tavily-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active