📌Overview

Purpose: To provide AI-powered web search capabilities through a Model Context Protocol server utilizing Tavily's search API.

Overview: The Tavily MCP Server enhances the capability of language models to perform advanced web searches, retrieve direct answers, and access recent news content with relevant AI-extracted data. It serves as a bridge between AI models and comprehensive web search functionalities.

Key Features:

• tavily_web_search: Enables comprehensive web searches, extracting AI-powered content to provide relevant information based on user queries.

• tavily_answer_search: Performs searches and generates direct answers supported by evidence, effectively addressing user inquiries for precise information.

• tavily_news_search: Facilitates the retrieval of recent news articles, allowing users to stay updated on current events by searching through a specified time frame.

---

Tavily MCP Server

A Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API. This server enables LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles with AI-extracted relevant content.

Features

Available Tools

• tavily_web_search: Performs comprehensive web searches with AI-powered content extraction.

  • query (string, required): Search query
  • max_results (integer, optional): Maximum number of results to return (default: 5, max: 20)
  • search_depth (string, optional): "basic" or "advanced" search depth (default: "basic")
  • include_domains (list or string, optional): List of domains to include
  • exclude_domains (list or string, optional): List of domains to exclude

• tavily_answer_search: Performs web searches and generates direct answers with supporting evidence.

  • query (string, required): Search query
  • max_results (integer, optional): Maximum number of results to return (default: 5, max: 20)
  • search_depth (string, optional): "basic" or "advanced" search depth (default: "advanced")
  • include_domains (list or string, optional): List of domains to include
  • exclude_domains (list or string, optional): List of domains to exclude

• tavily_news_search: Searches recent news articles with publication dates.

  • query (string, required): Search query
  • max_results (integer, optional): Maximum number of results to return (default: 5, max: 20)
  • days (integer, optional): Number of days back to search (default: 3)
  • include_domains (list or string, optional): List of domains to include
  • exclude_domains (list or string, optional): List of domains to exclude

Prompts

• tavily_web_search: Search the web using Tavily's AI-powered search engine
• tavily_answer_search: Search the web and get an AI-generated answer with supporting evidence
• tavily_news_search: Search recent news articles

Prerequisites

• Python 3.11 or later
• A Tavily API key
• uv Python package manager (recommended)

Installation

Option 1: Using pip or uv

pip install mcp-tavily
# Or with uv (recommended)
uv add mcp-tavily

Option 2: From source

git clone <repository-url>
cd mcp-tavily
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv sync  # Or: pip install -r requirements.txt
uv build  # Or: pip install -e .

Configuration

API Key Setup

The server requires a Tavily API key, which can be provided in three ways:

1. Through a .env file:

   TAVILY_API_KEY=your_api_key_here
   

2. As an environment variable:

   export TAVILY_API_KEY=your_api_key_here
   

3. As a command-line argument:

   python -m mcp_server_tavily --api-key=your_api_key_here
   

Usage Examples

• Regular web search:

  Tell me about Anthropic's newly released MCP protocol
  

• Report with domain filtering:

  Tell me about redwood trees. Exclude Wikipedia sources.
  

• Answer search mode:

  What is the average lifespan of redwood trees?
  

• News search:

  Give me the top 10 AI-related news in the last 5 days
  

Testing

To run the tests:

1. Install test dependencies:

   source .venv/bin/activate  # If using a virtual environment
   uv sync --dev  # Or: pip install -r requirements-dev.txt
   

2. Run the tests:

   ./tests/run_tests.sh
   

Debugging

Use the MCP inspector to debug the server:

npx @modelcontextprotocol/inspector python -m mcp_server_tavily

Contributing

To contribute:

1. Fork the repository
2. Create a feature branch
3. Make changes
4. Run tests
5. Commit changes
6. Push to the branch
7. Open a Pull Request

License

mcp-tavily is licensed under the MIT License. See the LICENSE file for details.