OpenRouter Web Search MCP Server

by ChristianSch

This project implements an MCP server that provides a `search_web` tool. The tool performs a web search using OpenRouter's online models to generate concise, up-to-date answers.

View on GitHub

Last updated: N/A

What is OpenRouter Web Search MCP Server?

This is an MCP (Model Context Protocol) server that provides a search_web tool. This tool leverages OpenRouter's online models to perform web searches and generate fact-based answers to queries.

How to use OpenRouter Web Search MCP Server?

Install Go 1.18+.
Obtain an OpenRouter API key.
Install the server using go install github.com/ChristianSch/openrouter-websearch-mcp.
Configure the server in your MCP configuration file, providing your OpenRouter API key as an environment variable.

Key features of OpenRouter Web Search MCP Server

Exposes an MCP-compatible server over stdio
Provides a search_web tool
Uses OpenRouter's online models for web search
Generates fact-based answers

Use cases of OpenRouter Web Search MCP Server

Answering questions that require up-to-date information
Providing context for AI models
Integrating web search capabilities into AI workflows
Automating research tasks

FAQ from OpenRouter Web Search MCP Server

What is MCP?

MCP stands for Model Context Protocol. It is a protocol for connecting AI models with external tools and data sources.

What is OpenRouter?

OpenRouter is a service that provides access to various AI models through a single API.

What models are supported?

Any OpenRouter model that supports the :online suffix can be used. The default model is google/gemini-2.5-pro-exp-03-25:free:online.

Is an OpenRouter API key required?

Yes, an OpenRouter API key is required to use this server.

How do I configure the server?

The server is configured using environment variables, specifically OPENROUTER_API_KEY and optionally MODEL_NAME.