OpenRouter Reasoning MCP
Enables multi-step AI reasoning by sending prompts to OpenRouter, performing a verification pass, and returning both responses with provider reasoning fields when available.
README
OpenRouter Reasoning MCP
A stateless remote Model Context Protocol (MCP) server running on Cloudflare Workers.
It exposes one tool, multi_step_reasoning, which sends a prompt to OpenRouter, performs a second verification pass, and returns both responses plus provider reasoning fields when available.
Architecture
MCP client
│
│ Streamable HTTP
▼
Cloudflare Worker /mcp
│
├── OpenRouter request #1
│
└── OpenRouter request #2 (verification)
│
▼
OpenRouter model
stealth/ox-alpha
Requirements
- Node.js
- A Cloudflare account
- An OpenRouter API key
- Wrangler authentication
Local development
npm install
npx wrangler login
npx wrangler secret put OPENROUTER_API_KEY
npm run dev
The MCP endpoint is /mcp.
Deploy
npm install
npx wrangler login
npx wrangler secret put OPENROUTER_API_KEY
npm run typecheck
npm run deploy
After deployment, the endpoint will be:
https://openrouter-reasoning-mcp.<your-subdomain>.workers.dev/mcp
MCP client configuration
Use the deployed /mcp URL as a remote MCP server using Streamable HTTP. Do not configure the endpoint as the deprecated HTTP+SSE transport.
Tool
multi_step_reasoning
Input:
{
"prompt": "Explain why a binary search is O(log n).",
"follow_up": "Verify the explanation and correct any mistakes."
}
follow_up is optional. The default is:
Are you sure? Think carefully and verify your answer.
Security
The OpenRouter key is stored as a Cloudflare Worker secret and is never committed to Git. The current server is intentionally unauthenticated, meaning anyone who can reach the /mcp endpoint can invoke the tool and consume the configured OpenRouter account. Add MCP authentication/authorization before using this publicly with a paid OpenRouter key.
License
MIT
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.
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.
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.
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.