mcp-tavily

mcp-tavily

54

Tavily MCP Server is a Model Context Protocol server designed to enable AI-powered web search capabilities. It provides tools for comprehensive web searches and direct AI-generated answers, utilizing Tavily's search API. Key features include the ability to filter searches by domain and gather recent news articles.

What is the Tavily MCP Server?

The Tavily MCP Server is a Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform advanced web searches and obtain direct answers.

What are the prerequisites for using the Tavily MCP Server?

You need Python 3.11 or later, a Tavily API key, and the 'uv' Python package manager is recommended for installation.

How can I install the Tavily MCP Server?

You can install it using pip or uv, or from source by cloning the repository and setting up a virtual environment.

How do I configure the API key for the server?

The API key can be configured through a .env file, as an environment variable, or as a command-line argument.

What types of searches can the Tavily MCP Server perform?

It can perform web searches, generate direct answers with evidence, and search recent news articles.