OpenRouter MCP server

The OpenRouter MCP Multimodal Server provides chat and image analysis capabilities through OpenRouter.ai's diverse model ecosystem, combining text chat functionality with powerful image analysis in a unified interface.

Installation

Using npm

Install the package globally using npm:

npm install -g @stabgan/openrouter-mcp-multimodal

Using Docker

Run the server directly with Docker:

docker run -i -e OPENROUTER_API_KEY=your-api-key-here stabgandocker/openrouter-mcp-multimodal:latest

Configuration

Prerequisites

Before setting up the server, you'll need:

1. An OpenRouter API key from OpenRouter Keys
2. Optionally, a default model selection

Setup Options

Add one of these configurations to your MCP settings file:

Using npx (Node.js)

{
  "mcpServers": {
    "openrouter": {
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-api-key-here",
        "DEFAULT_MODEL": "qwen/qwen2.5-vl-32b-instruct:free"
      }
    }
  }
}

Using uv (Python Package Manager)

{
  "mcpServers": {
    "openrouter": {
      "command": "uv",
      "args": [
        "run",
        "-m",
        "openrouter_mcp_multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-api-key-here",
        "DEFAULT_MODEL": "qwen/qwen2.5-vl-32b-instruct:free"
      }
    }
  }
}

Using Docker

{
  "mcpServers": {
    "openrouter": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "OPENROUTER_API_KEY=your-api-key-here",
        "-e", "DEFAULT_MODEL=qwen/qwen2.5-vl-32b-instruct:free",
        "stabgandocker/openrouter-mcp-multimodal:latest"
      ]
    }
  }
}

Using Smithery (Recommended)

{
  "mcpServers": {
    "openrouter": {
      "command": "smithery",
      "args": [
        "run",
        "stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-api-key-here",
        "DEFAULT_MODEL": "qwen/qwen2.5-vl-32b-instruct:free"
      }
    }
  }
}

Usage

Text Chat Example

To send a simple text chat message:

use_mcp_tool({
  server_name: "openrouter",
  tool_name: "mcp_openrouter_chat_completion",
  arguments: {
    model: "google/gemini-2.5-pro-exp-03-25:free", // Optional if default is set
    messages: [
      {
        role: "system",
        content: "You are a helpful assistant."
      },
      {
        role: "user",
        content: "What is the capital of France?"
      }
    ],
    temperature: 0.7 // Optional, defaults to 1.0
  }
});

Multimodal Chat Example

For sending messages that include images:

use_mcp_tool({
  server_name: "openrouter",
  tool_name: "mcp_openrouter_chat_completion",
  arguments: {
    model: "anthropic/claude-3.5-sonnet",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "text",
            text: "What's in this image?"
          },
          {
            type: "image_url",
            image_url: {
              url: "https://example.com/image.jpg"
            }
          }
        ]
      }
    ]
  }
});

Features and Capabilities

Text Chat

• Access to all OpenRouter.ai chat models
• Support for simple text and multimodal conversations
• Configurable parameters like temperature

Image Analysis

• Analyze single or multiple images with custom questions
• Automatic image resizing and optimization
• Support for various image sources (local files, URLs, data URLs)

Model Selection

• Search and filter available models
• Get detailed model information
• Support for default model configuration

Performance Features

• Smart model information caching
• Exponential backoff for retries
• Automatic rate limit handling

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.