mcpField
M
MCP Bench Router

MCP Bench Router

Local
github.com/K1ta141kAI & Agents7Updated 38w ago
Repository

About MCP Bench Router

MCP Bench Router is an MCP server for clients that delegate design tasks to models ranked by designarena.ai. It checks the current leaderboard and routes prompts to the top available model through OpenRouter, or to a specified model.

Key features

  1. 01Find the top-ranked design model
  2. 02Browse filtered, paginated rankings
  3. 03Route prompts to the top available model
  4. 04Query a specified model through OpenRouter

Use cases

  1. 01Check the leading model for a design category
  2. 02Review top-ranked models for website design
  3. 03Delegate a design prompt to the current leader
  4. 04Send a prompt to a chosen model

MCP support

Exposes leaderboard and model-query tools to MCP clients. It routes model prompts through OpenRouter; an API key is required for querying models.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "k1ta141k-mcp-bench-router": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bench-router"
      ],
      "env": {
        "OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
      }
    }
  }
}
Run commandnpx -y mcp-bench-router
Environment variables to set
OPENROUTER_API_KEYSecretOpenRouter API key for query_design_model and query_specific_model tools. Get one at https://openrouter.ai/keys

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-bench-router1.0.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
categoryenumNoDesign category to filter by. Options: allcategories, website (models generate a complete website from a text prompt), gamedev (models generate a playable browser game from a text prompt), 3d (models generate an interactive 3d scene from a text prompt), dataviz (models generate interactive data visualizations from a text prompt), uicomponent (models generate a production-ready ui component from a text prompt), image (models generate an image from a text prompt), logo (models generate a logo design from a text prompt), svg (models generate svg markup from a text prompt), video (models generate a video from a text prompt), imagetoimage (models transform an existing image based on a text prompt), slides (models generate a presentation from a text prompt), graphicdesign (models generate graphic design assets (posters, banners, marketing materials) from a text prompt), tts (models generate speech audio from text input). Defaults to "allcategories".allcategories | website | gamedev | 3d | dataviz | uicomponent | image | logo | svg | video | imagetoimage | slides | graphicdesign | tts

Details

From the project README

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

ToolDescription
get_best_design_modelGet the current #1 design model, optionally by category
get_leaderboardBrowse full rankings with category filter and pagination
query_design_modelSend a prompt to the best available model via OpenRouter
query_specific_modelSend 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

Categories

Filter by design category: allcategories, website, gamedev, 3d, dataviz, uicomponent, image, logo, svg, video, imagetoimage, slides, graphicdesign, tts.

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

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

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.