OpenRouter LLM Gateway

v1.0.0APIsstable

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

ai-agentclaudeclaude-desktopcursordocker
Share:
40
Stars
0
Downloads
0
Weekly
0/5

What is OpenRouter LLM Gateway?

OpenRouter LLM Gateway is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for openrouter — chat with 300+ llms (claude, gemini, gpt), analyze images / audio / video, generate images / speech / music / video (veo 3.1, sora, seedance, wan) from claude desktop, curs...

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gem

Use Cases

Multi-LLM access
Multimodal inference
stabgan

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @stabgan/openrouter-mcp-multimodal

Manual Installation

npx -y @stabgan/openrouter-mcp-multimodal

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use OpenRouter LLM Gateway

The OpenRouter MCP Multimodal server connects AI clients such as Claude Desktop, Cursor, and VS Code to OpenRouter's gateway, giving them access to 300+ language models — including Claude, Gemini, and GPT variants — alongside multimodal capabilities for image analysis, audio processing, and video generation. It exposes 14 tools covering chat completion, media analysis, AI-powered video and image generation (Veo 3.1, Sora 2 Pro), audio creation, model search, and health checks, all secured with SSRF protection and path sandboxing.

Prerequisites

  • Node.js 18 or later installed
  • An OpenRouter API key obtained from openrouter.ai/keys
  • An MCP-compatible client: Claude Desktop, Cursor, VS Code, or Kiro
  • Docker (optional, for containerized deployment)
1

Obtain an OpenRouter API key

Sign up at openrouter.ai and navigate to openrouter.ai/keys to create a free API key. Copy it — you will need it in the configuration step.

2

Test the package with npx

Run the server once via npx to confirm Node.js and the package are working correctly before wiring it into a client.

OPENROUTER_API_KEY=your-key-here npx -y @stabgan/openrouter-mcp-multimodal
3

Configure Claude Desktop

Add the server block to ~/Library/Application Support/Claude/claude_desktop_config.json with your API key set as an environment variable.

{
  "mcpServers": {
    "openrouter": {
      "command": "npx",
      "args": ["-y", "@stabgan/openrouter-mcp-multimodal"],
      "env": {
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}
4

Set optional configuration variables

Override the default model, output directory, or log level using additional environment variables in the env block.

"OPENROUTER_DEFAULT_MODEL": "anthropic/claude-sonnet-4",
"OPENROUTER_OUTPUT_DIR": "/Users/yourname/ai-output",
"OPENROUTER_LOG_LEVEL": "info"
5

Restart your MCP client and verify

Reload Claude Desktop or your chosen client. The 14 OpenRouter tools (chat_completion, analyze_image, generate_video, etc.) should appear. Run a health check prompt to confirm.

OpenRouter LLM Gateway Examples

Client configuration

Full claude_desktop_config.json entry for the OpenRouter MCP Multimodal server.

{
  "mcpServers": {
    "openrouter": {
      "command": "npx",
      "args": ["-y", "@stabgan/openrouter-mcp-multimodal"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-your-key-here",
        "OPENROUTER_DEFAULT_MODEL": "nvidia/nemotron-nano-12b-v2-vl:free",
        "OPENROUTER_OUTPUT_DIR": "/Users/yourname/Downloads/ai-output",
        "OPENROUTER_LOG_LEVEL": "warn"
      }
    }
  }
}

Prompts to try

Example prompts covering chat, image analysis, and video generation.

- "Using OpenRouter, chat with google/gemini-2.5-pro and ask it to explain transformer attention"
- "Analyze this image at /Users/me/screenshot.png and describe what you see"
- "Search for the cheapest model that supports vision tasks on OpenRouter"
- "Generate a short video of a cinematic river sunrise using Veo 3.1 and save it to my output folder"
- "Using OpenRouter, compare the response from claude-sonnet-4 and gpt-4o on the question: what is consciousness?"

Troubleshooting OpenRouter LLM Gateway

Authentication error: invalid or missing API key

Ensure OPENROUTER_API_KEY is set exactly as shown without extra spaces or quotes. Verify the key is active by visiting openrouter.ai/keys. The key must begin with sk-or-v1-.

Path error when saving generated media

Set OPENROUTER_OUTPUT_DIR to an absolute path that exists and is writable. If you need to save files outside the sandbox, also set OPENROUTER_ALLOW_UNSAFE_PATHS=1, but be aware this disables path traversal protection.

Video generation returns a status URL instead of a file

Video generation is asynchronous. Use the get_video_status tool with the returned job ID to poll for completion. Once the status is 'completed', the tool will provide a download URL or save the file to your output directory.

Frequently Asked Questions about OpenRouter LLM Gateway

What is OpenRouter LLM Gateway?

OpenRouter LLM Gateway is a Model Context Protocol (MCP) server that mcp server for openrouter — chat with 300+ llms (claude, gemini, gpt), analyze images / audio / video, generate images / speech / music / video (veo 3.1, sora, seedance, wan) from claude desktop, cursor, kiro, vs code. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install OpenRouter LLM Gateway?

Install via npm with the command: npx -y @stabgan/openrouter-mcp-multimodal. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with OpenRouter LLM Gateway?

OpenRouter LLM Gateway works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is OpenRouter LLM Gateway free to use?

Yes, OpenRouter LLM Gateway is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "openrouter-mcp-multimodal": { "command": "npx", "args": ["-y", "@stabgan/openrouter-mcp-multimodal"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use OpenRouter LLM Gateway?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides