fusion-mcp
Click on "Install 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., "@fusion-mcpresearch the pros and cons of quantum computing"
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.
fusion-mcp
A zero-dependency MCP server that exposes OpenRouter Fusion as a tool any agent can call.
Fusion sends your prompt to a panel of models in parallel (with web search), a judge model compares their answers, and you get back one synthesized answer — stronger than any single model. This wraps it so Claude Code (or any MCP client) can reach Fusion directly instead of going through the OpenRouter web UI.
Tool
fusion_ask
arg | required | description |
| ✅ | The question or task for the Fusion panel. |
| 1–8 model slugs forming the panel. Omit for Fusion's default preset. | |
| Model that synthesizes the panel's answers. Defaults to the first panel model. | |
| Curated preset: | |
| Tool iterations per panel model (1–16, default 8). |
Fusion runs several completions per call (panel + judge), so it costs more than a single model call. Use it where being wrong is costly: research, critique, decisions.
Related MCP server: cognition-wheel
Setup
Requires Node ≥ 18 and an OpenRouter API key.
export OPENROUTER_API_KEY=sk-or-...Wire into Claude Code
claude mcp add fusion -e OPENROUTER_API_KEY=sk-or-... -- node /Users/yoshikondo/fusion-mcp/server.mjsOr add to your MCP config manually:
{
"mcpServers": {
"fusion": {
"command": "node",
"args": ["/Users/yoshikondo/fusion-mcp/server.mjs"],
"env": { "OPENROUTER_API_KEY": "sk-or-..." }
}
}
}Then in a session: "use fusion_ask to research X".
Test
npm testThe test suite spins up a real local HTTP server standing in for OpenRouter and drives a real child-process MCP server over real stdio — nothing internal is mocked.
License
MIT
This server cannot be installed
Maintenance
Related MCP Servers
- AlicenseAqualityCmaintenanceAn MCP server that enables users to query, compare, and synthesize responses from multiple local and cloud LLMs simultaneously using existing subscriptions. It provides tools for parallel model evaluation, consensus polling with an LLM-as-judge, and response synthesis across different model providers.Last updated83215MIT
- AlicenseAqualityDmaintenanceEnables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.Last updated111194MIT
- Alicense-qualityBmaintenanceAn MCP server that queries a panel of LLMs from different providers via OpenRouter and returns their answers side by side, optionally synthesizing them to highlight disagreements.Last updated271MIT
- FlicenseAqualityCmaintenanceMulti-model fusion analysis tool that sends queries to multiple AI models in parallel and returns structured analysis from a judge model.Last updated1
Related MCP Connectors
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yksanjo/fusion-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server