MCP Bench Router Server

Claude Code sucks at design. Let it delegate it's tasks to better models. Claude will use the MCP to get leaderboard of best design models and query specific code changes using OpenRouter.

GitHub

Documentation

mcp-bench-router

MCP server that delegates design tasks to whichever model currently tops designarena.ai's crowdsourced leaderboard, via OpenRouter.

Why?

AI coding assistants produce mediocre frontend/design output. designarena.ai maintains a live leaderboard of the best design models, updated every 2 hours. This MCP server lets Claude (or any MCP client) automatically route design tasks to the current best model.

Tools

Tool	Description
`get_best_design_model`	Get the current #1 design model, optionally by category
`get_leaderboard`	Browse full rankings with category filter and pagination
`query_design_model`	Send a prompt to the best available model via OpenRouter
`query_specific_model`	Send a prompt to a specific model via OpenRouter

Setup

Prerequisites

Node.js >= 18
An OpenRouter API key (required for query_design_model and query_specific_model)

Claude Code (CLI)

claude mcp add mcp-bench-router -s user -e OPENROUTER_API_KEY=sk-or-... -- npx -y mcp-bench-router

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "mcp-bench-router": {
      "command": "npx",
      "args": ["-y", "mcp-bench-router"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-..."
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "mcp-bench-router": {
      "command": "npx",
      "args": ["-y", "mcp-bench-router"],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-..."
      }
    }
  }
}

Other MCP clients

OPENROUTER_API_KEY=sk-or-... npx -y mcp-bench-router

From source

git clone https://github.com/K1ta141k/mcp-bench-router.git
cd mcp-bench-router
npm install
npm run build

Usage Examples

Check who's #1:

"Use get_best_design_model to see the current top design model"

Browse rankings:

"Show me the top 20 design models for websites"

Generate a design:

"Use query_design_model to create a landing page for a SaaS product"

Use a specific model:

"Use query_specific_model with claude-sonnet-4-5 to design a dashboard"

How It Works

Fetches live rankings from designarena.ai's API (cached 2hr)
Maps arena model names to OpenRouter IDs (static + dynamic + fuzzy matching)
Skips codename/unreleased models and picks the best available one
Routes the prompt through OpenRouter's API

License

MIT