rapidrouter-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@rapidrouter-mcpfind a model with 200k context and price under $2 per million tokens"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
rapidrouter-mcp
An MCP (Model Context Protocol) stdio server for Rapid Router, the AI gateway with an OpenAI-compatible API. It lets any MCP client (Claude Desktop, Claude Code, Cursor, and others) search the live model catalog, look up prices in USD and INR, send chat completions, and check your credit balance.
Install
Once published to npm:
npx rapidrouter-mcpFrom source, today:
cd mcp && npm install
node mcp/index.jsThe server speaks MCP over stdin/stdout. chat and account_balance need a Rapid Router
API key in the RAPIDROUTER_API_KEY environment variable; get one at
https://rapidrouter.ai/dashboard/keys. The catalog tools need no key.
Related MCP server: yuntu-mcp-server
Client configuration
Claude Desktop (claude_desktop_config.json) and Cursor (.cursor/mcp.json) use the
same mcpServers shape:
{
"mcpServers": {
"rapidrouter": {
"command": "npx",
"args": ["rapidrouter-mcp"],
"env": { "RAPIDROUTER_API_KEY": "rr-..." }
}
}
}Claude Code:
claude mcp add rapidrouter -e RAPIDROUTER_API_KEY=rr-... -- npx rapidrouter-mcpRunning from a checkout instead of npm, replace the command with
"command": "node", "args": ["/path/to/rapid-router/mcp/index.js"].
Tools
Tool | Auth | What it does |
| none | Search live models by substring on id/name/author, with optional |
| none | One model's full catalog row by exact id, plus INR prices from the catalog's live USD/INR rate. |
|
| Send a prompt (optional |
|
| Your credit balance in USD and INR. |
Run rapidrouter-mcp --help for a usage summary.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for UnoRouter, an OpenAI-compatible gateway with 200+ models, providing search_models, get_pricing, and chat tools to interact with various AI models through natural language.378 npmAGPL 3.0
- FlicenseAqualityBmaintenanceEnables LLM chat with routing and failover, balance checking, and model listing via MCP.3-
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to browse a live catalog of 100+ models with pricing, rankings and measured uptime, check credits and spend, and send chat completions through an OAuth-authenticated, per-connection key capped by a spend limit. Read tools are free, and paid calls are priced and approved before any credit is used.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to discover and inspect available open models, estimate token costs, and run chat completions through an OpenAI-compatible inference endpoint, with optional bearer-key authentication for billed calls.Apache 2.0