MCP Tavily Web Search Server

🚀 Web Search MCP Server

A Model Context Protocol (MCP) server implemented using Tavily API that provides a web search tool. This server enables AI models to access the internet and retrieve the latest information.

🚀 Quick Start

The Web Search MCP Server serves as a bridge between AI models and the Tavily search engine, allowing models to access current internet information during conversations.

# Run the server using uv
uv run web_search_server.py

✨ Features

Real - time Web Search

The server offers real - time web search capabilities, enabling AI models to obtain up - to - date information.

Customizable Search Parameters

• Search Topic: Options include "general", "news", and "finance".
• Search Depth: You can choose between "basic" and "advanced".
• Maximum Results: Specify the maximum number of results to return.
• Time Range Filter: Filter results by time range, such as days, weeks, months, or years.
• Domain Inclusion/Exclusion: Include or exclude specific domains from the search.

📦 Installation

Prerequisites

• Python 3.13+
• uv - A Python package installer and resolver
• Tavily API key (Register at tavily.com)

Steps

1. Clone the repository if necessary.
2. Create a virtual environment using uv (optional but recommended):

   uv venv
   # Activate the virtual environment
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   

3. Install dependencies using uv:

   uv pip sync
   

📚 Documentation

Configuration

1. Create a .env file by copying the provided template:

   cp env - sample .env
   

2. Add your Tavily API key to the .env file:

   TAVILY_API_KEY=your - api - key - here
   

Tool Parameters

The search_web_tool accepts the following parameters:

Response Format

The tool returns a list of search results, where each result contains:

• title: The title of the search result.
• url: The URL of the search result.
• content: The content of the search result.
• score: The relevance score of the search result.

Error Handling

If an error occurs during the search operation, the tool will return an error message describing the problem.