OpenRouter MCP Client for Cursor

- Connect to OpenRouter.ai via MCP
- Access multiple AI models from various providers (Google, DeepSeek, Meta, etc.)
- Use MCP transport mechanism to communicate with Cursor
- Cache model information to reduce API calls
- Support for both free and paid models
- Multi-model completion utility to combine results from multiple models

This client provides access to all models available on OpenRouter, including:

- Google Gemini 2.5 Pro
- DeepSeek Chat v3
- Meta Llama 3.1
- DeepSeek R1
- Qwen Coder
- Mistral Small 3.1
- And many more!

The easiest way to install is to use the setup script:

# Clone the repository git clone https://your-repo-url/openrouter-mcp-client.git cd openrouter-mcp-client # Run the installation script node install.cjs

- Help you create a.envfile with your OpenRouter API key
- Install all dependencies
- Build the project
- Provide next steps

# Clone the repository git clone https://your-repo-url/openrouter-mcp-client.git cd openrouter-mcp-client # Install dependencies npm install # Copy environment file and edit it with your API key cp .env.example .env # Edit .env file with your OpenRouter API key # Build the project npm run build

Edit the.envfile with your OpenRouter API key and default model:

OPENROUTER_API_KEY=your_api_key_here OPENROUTER_DEFAULT_MODEL=google/gemini-2.5-pro-exp-03-25:free

To use this client with Cursor, you need to update Cursor's MCP configuration file:
-

Find Cursor's configuration directory:

- Windows:%USERPROFILE%\.cursor\
- macOS:~/.cursor/
- Linux:~/.cursor/

Edit or create themcp.jsonfile in that directory. Add a configuration like this:

If you encounter errors related to ES modules vs CommonJS:

- The main codebase uses ES modules (indicated by"type": "module"in package.json)
- The installation script uses CommonJS (with a .cjs extension)
- Make sure to run the installation script withnode install.cjs

If Cursor doesn't seem to connect to your client:
- Make sure the path inmcp.jsonis correct and uses forward slashes
- Check that you've built the client withnpm run build
- Verify that your OpenRouter API key is correct in the env settings
- Check Cursor logs for any errors

Fork this repositoryto your GitHub account

- Click "Add Server" in the Smithery dashboard
- Select your forked repository
- Configure the build settings:

- Set the base directory to the repository root
- Ensure the Dockerfile and smithery.yaml are detected

- Smithery will automatically build and deploy your MCP server
- Once deployed, users can configure it with their own OpenRouter API key

After deployment, users can access your server through the Smithery registry:
- In their MCP client (like Claude, or any other MCP-compatible client), add the server using Smithery's registry
- Configure their OpenRouter API key and preferred default model
- Start using the server to access multiple AI models through OpenRouter

- Smithery: Easier for distribution to others; no need for users to clone and build the repository
- Local Installation: Better for personal use and development; more control over the environment

Choose the approach that best fits your needs.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Access 30+ AI models in Claude Code with zero API keys. One wallet, pay-per-request.

Remote Streamable HTTP MCP gateway for GPT-5.5 chat plus 92 text, web, JSON, and x402 discovery tools with Base USDC pay-per-call.

Deploy and serve Haystack pipelines as REST APIs, MCP Tools, and OpenAI-compatible chat completion backends.

JCode Harness Cloud is a paid remote MCP endpoint for OpenAI Codex harness MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready wo

Provides educational content, model information, and read-only API interactions for Lerian developers.

A command-line interface wrapper for the Google Gemini API, enabling interaction with Gemini's Search and Chat tools.

A backend service providing tools, resources, and prompts for AI models using the Model Context Protocol (MCP).

A bridge API service connecting Ollama with Model Context Protocol (MCP) servers.

MCP server for OpenRouter — chat with any model through one API key