openrouter-search-server

openrouter-search-server

5

The OpenRouter Search MCP Server is a Model Context Protocol server designed to perform web searches using the OpenRouter API, returning raw text output. It integrates with MCP clients using a specific AI model, providing web search capabilities efficiently.

OpenRouter Search MCP Server

This project is a Model Context Protocol (MCP) server designed to provide web search capabilities using the OpenRouter API.

Features

  • Web Search via OpenRouter: Utilizes the OpenRouter API for web searches.
  • Specific Model: Features the google/gemini-2.5-pro-preview-03-25 model.
  • Raw Text Output: Provides unparsed text responses from the AI model.
  • MCP Integration: Offers a web_search tool compatible with MCP clients.

Installation

  1. Clone the repository.
  2. Install dependencies with npm.
  3. Build the TypeScript code.

Configuration

Set up requires an API key from OpenRouter and adjustments to MCP client's settings file.

Usage

The server operates using the web_search tool, requiring a search query input to deliver raw text output from the OpenRouter API model.