NosytLabs/presearch-mcp-server

Presearch MCP Server

Official Presearch MCP Server for seamless integration with AI models, providing powerful, decentralized search capabilities.

Features

• Simplified Error Handling: Robust error categorization and retry mechanisms.
• Enhanced Performance: Optimized with rate limiting and circuit breakers.
• Easy Configuration: Simplified setup with environment variables.
• Caching: Efficient caching for repeated searches.
• Testing: Comprehensive unit tests for reliability.

Prerequisites

• Node.js >= 18.x
• npm >= 9.x
• A Presearch API key (obtain from Presearch)

Installation

1. Clone the repository:

   git clone https://github.com/NosytLabs/presearch-mcp-server.git
   cd presearch-mcp-server
   

2. Install dependencies:

   npm install
   

3. Build the project (TypeScript to JavaScript):

   npm run build
   

Configuration

• Copy .env.example to .env and add your PRESEARCH_API_KEY:

  PRESEARCH_API_KEY=your_api_key_here
  

Running the Server

npm start

The server will run on the configured port (default: 3000).

Usage

Available Tools

• presearch_search: Perform web searches.

  • Parameters: query (string), num (number, optional), lr (string, optional)
  • Example: {"query": "latest AI news"}

• presearch_cache_clear: Clear the search cache.

For detailed usage and parameters, refer to the mcp.config.json file.

Testing

Run the tests:

npm test

All tests should pass, ensuring the server's reliability.

Contributing

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Add some AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).
5. Open a Pull Request.

License

This project is licensed under the MIT License - see the file for details.