Tavily

An MCP server for Tavily's search API

python

72

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ramxx-mcp-tavily": {
      "command": "python",
      "args": [
        "-m",
        "mcp_server_tavily"
      ],
      "env": {
        "TAVILY_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run a Tavily-powered MCP Server that exposes AI-assisted web search, direct answers with evidence, and recent-news search to your language models. This server lets AI systems perform sophisticated web queries through Model Context Protocol endpoints, returning structured results you can feed into your LLM prompts.

How to use

Start your Tavily MCP Server using your preferred Python runtime and API key. Once running, you can query the server through an MCP client to perform web searches, get AI-generated answers with sources, or fetch recent news with dates. Use the three available tools to guide your LLMs toward the right data sources and presentation format.

How to install

Prerequisites: You need Python 3.11 or later.

Install the Tavily MCP package either with pip or uvx.

# With pip
pip install mcp-tavily

# Or with uvx (recommended)
uv add mcp-tavily

Run the server with your Tavily API key. You can pass the key as an environment variable or via a command-line option.

# Use an environment variable
export TAVILY_API_KEY=your_api_key_here
python -m mcp_server_tavily

# Or pass the key directly (not recommended for production)
python -m mcp_server_tavily --api-key=your_api_key_here

Optionally, you can provide the key in your environment or a .env file in your project folder.

Configuration and usage notes

Set up the Tavily API key in one of the following ways.

# In a .env file
TAVILY_API_KEY=your_api_key_here

# As a direct environment variable
export TAVILY_API_KEY=your_api_key_here

# Or in a command line (for quick testing)
python -m mcp_server_tavily --api-key=your_api_key_here

Available tools

tavily_web_search

Performs comprehensive web searches with AI-powered content extraction using Tavily's search API.

tavily_answer_search

Performs web searches and generates direct answers with supporting evidence.

tavily_news_search

Searches recent news articles with publication dates.