Tavily MCP Server Pg0

🚀 Tavily MCP Server

A server based on the Model Context Protocol (MCP) that leverages the Tavily API to provide AI - powered search capabilities. This server enables AI assistants to perform comprehensive web searches and retrieve relevant and up - to - date information.

🚀 Quick Start

The Tavily MCP Server is a powerful tool for AI - assisted web searches. It provides a wide range of features and is easy to set up and use.

✨ Features

• AI - powered search functionality
• Support for basic and advanced search depths
• Rich search results including titles, URLs, and content snippets
• AI - generated summaries of search results
• Result scoring and response time tracking
• Comprehensive history storage and caching
• Flexible data access through MCP resources

📦 Installation

Prerequisites

• Node.js (v16 or higher)
• npm (Node Package Manager)
• Tavily API key (obtainable from the Tavily website)
• Any MCP client (e.g., Cline, Claude Desktop, or other custom implementations)

Installation Steps

1. Clone the repository:

git clone https://github.com/it-beard/tavily-server.git
cd tavily-mcp-server

2. Install dependencies:

npm install

3. Build the project:

npm run build

📚 Documentation

Configuration

Project Structure

tavily-server/
├── src/
│   └── index.ts    # Main server implementation file
├── data/           # Persistent storage directory
│   └── searches.json  # Location for search history and cache storage
├── build/          # Compiled JavaScript output files
├── package.json    # Project dependencies and script configurations
└── tsconfig.json   # TypeScript compilation configuration

Usage

Starting the Server

npm run start

Resource Access

Search Results Interface

interface SearchResults {
  results: Array<{
    title: string;
    url: string;
    content: string;
    relevance: number;
  }>;
  total: number;
  took: number;
}

Persistent Storage

Storage Location

• Data is stored in the data directory.
• data/searches.json contains all search history records.
• Data is retained after server restarts.
• The storage format is JSON for easy debugging and viewing.
• Errors in storage operations are automatically handled.
• The required directory structure is automatically created.

Development Information

Available Script Commands

• npm run build: Compile TypeScript code and generate executable files.
• npm run start: Start the MCP server (requires prior compilation).
• npm run dev: Run the server in development mode.

Error Handling

This server provides detailed error messages to help diagnose common issues:

• Invalid API key
• Network connection issues
• Incorrect search parameters
• API rate limits
• Resource not found
• Invalid resource URI
• Storage read/write failures

Contribution Guidelines

1. Fork the repository to your local machine.
2. Create a feature branch (e.g., git checkout -b feature/amazing-feature).
3. Commit your changes (e.g., git commit -m 'Add amazing feature').
4. Push to the remote branch (e.g., git push origin feature/amazing-feature).
5. Submit a Pull Request.

📄 License

This project is licensed under the MIT License. Please refer to the LICENSE file for specific terms.

Acknowledgments

Thanks to the following projects and technologies for their support:

• Model Context Protocol (MCP) for providing the foundation for the server framework.
• Tavily API for providing the technical support for the search functionality.