Overview: tavily-search MCP Server
Title
tavily-search MCP Server – A server project that leverages the Tavily API to perform web searches and return structured results.
How to Use
-
Installation:
- Automatically via Smithery (
npx -y @smithery/cli install tavily-search --client claude).
- Manually by cloning the repository and configuring Claude Desktop or Cursor.
- Using Docker Compose for local environments.
-
Configuration:
- Set the
TAVILY_API_KEY in the environment variables.
- Adjust the Claude Desktop or Cursor settings to point to the server.
-
Execution:
- Query Claude Desktop or Cursor with search requests (e.g., "Please search for today's events in Kamakura").
Key Features
- Search Functionality:
- Performs web searches using the Tavily API.
- Supports basic and advanced search depths.
- Structured Results:
- Returns AI-generated summaries, URIs, and titles of search results.
- Multi-Platform Support:
- Works with Claude Desktop, Cursor, and local Docker environments.
- Logging:
- Stores logs in a designated directory for debugging.
Use Cases
- Information Retrieval: Quickly fetch and summarize web search results.
- Integration with AI Assistants: Enhance Claude or Cursor with real-time search capabilities.
- Local Development: Test and deploy the MCP server in isolated environments using Docker.
