OpenRouter Model Selector MCP
MCP server that helps AI assistants automatically find, filter, and rank the best AI models for a specific task using the OpenRouter API.
README
OpenRouter Model Selector MCP
OpenRouter Model Selector is a Model Context Protocol (MCP) server that helps AI assistants automatically find, filter, and rank the best AI models for a specific task using the OpenRouter API.
Whether you need a model for coding, image generation, text-to-speech (TTS), or transcription (STT), this tool queries the live OpenRouter directory, groups them by your requested modality, and ranks the top 10 models based on:
- Price (1 to 5 stars - 5 stars being the most expensive).
- Benchmark / Performance (1 to 5 stars based on intelligence index or Elo rating).
Features
- Zero Configuration: No API keys required. It uses OpenRouter's public
/api/v1/modelsendpoint. - Smart Modality Routing: Understands keywords to correctly filter for
image-understanding,video-understanding,transcription,speech,image-generation, andvideo-generation. - Dynamic Pricing Calculation: Accurately compares prompt/completion/image output prices to give a relative cost score.
- FastMCP Built: Built on top of
fastmcpfor quick integration with MCP-compatible clients like Claude Desktop, Cursor, or Google Antigravity.
Installation
- Clone this repository:
git clone https://github.com/your-username/openrouter-model-selector-mcp.git
cd openrouter-model-selector-mcp
- Create a virtual environment and install dependencies:
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Usage & Configuration
To use this with any MCP-compatible AI assistant, you need to add it to your MCP configuration file (e.g., mcp.json or claude_desktop_config.json).
Here is an example configuration:
{
"mcpServers": {
"openrouter-model-selector": {
"command": "/absolute/path/to/your/cloned/repo/.venv/bin/python",
"args": [
"/absolute/path/to/your/cloned/repo/openrouter_agent_selector.py"
]
}
}
}
Make sure to replace /absolute/path/to/your/cloned/repo/ with the actual path on your machine.
How it works
When connected, your AI assistant will have access to a tool called select_best_agent.
If you ask your AI: "Find me an AI model for text to speech", it will call this tool with topic="text to speech", fetch the relevant models, and present you with a Markdown-formatted list containing the stars for Price and Benchmark.
Security & Privacy
This tool does not require or transmit any private API keys. It only reads public model catalog data from OpenRouter.
License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.