{
  "markdown": "# mcp-bench-router\n\nMCP server that delegates design tasks to whichever model currently tops [designarena.ai](https://www.designarena.ai)'s crowdsourced leaderboard, via [OpenRouter](https://openrouter.ai).\n\n## Why?\n\nAI 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.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_best_design_model` | Get the current #1 design model, optionally by category |\n| `get_leaderboard` | Browse full rankings with category filter and pagination |\n| `query_design_model` | Send a prompt to the best available model via OpenRouter |\n| `query_specific_model` | Send a prompt to a specific model via OpenRouter |\n\n## Setup\n\n### Prerequisites\n\n- Node.js >= 18\n- An [OpenRouter API key](https://openrouter.ai/keys) (required for `query_design_model` and `query_specific_model`)\n\n### Claude Code (CLI)\n\n```bash\nclaude mcp add mcp-bench-router -s user -e OPENROUTER_API_KEY=sk-or-... -- npx -y mcp-bench-router\n```\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-bench-router\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-bench-router\"],\n      \"env\": {\n        \"OPENROUTER_API_KEY\": \"sk-or-...\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project root:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-bench-router\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-bench-router\"],\n      \"env\": {\n        \"OPENROUTER_API_KEY\": \"sk-or-...\"\n      }\n    }\n  }\n}\n```\n\n### Other MCP clients\n\n```bash\nOPENROUTER_API_KEY=sk-or-... npx -y mcp-bench-router\n```\n\n### From source\n\n```bash\ngit clone https://github.com/K1ta141k/mcp-bench-router.git\ncd mcp-bench-router\nnpm install\nnpm run build\n```\n\n## Categories\n\nFilter by design category: `allcategories`, `website`, `gamedev`, `3d`, `dataviz`, `uicomponent`, `image`, `logo`, `svg`, `video`, `imagetoimage`, `slides`, `graphicdesign`, `tts`.\n\n## Usage Examples\n\n**Check who's #1:**\n> \"Use get_best_design_model to see the current top design model\"\n\n**Browse rankings:**\n> \"Show me the top 20 design models for websites\"\n\n**Generate a design:**\n> \"Use query_design_model to create a landing page for a SaaS product\"\n\n**Use a specific model:**\n> \"Use query_specific_model with claude-sonnet-4-5 to design a dashboard\"\n\n## How It Works\n\n1. Fetches live rankings from designarena.ai's API (cached 2hr)\n2. Maps arena model names to OpenRouter IDs (static + dynamic + fuzzy matching)\n3. Skips codename/unreleased models and picks the best available one\n4. Routes the prompt through OpenRouter's API\n\n## License\n\nMIT\n",
  "bytes": 2881,
  "sha": "5f0b825d002cde976a150cb37dc12b514776e2b74c6081c4ed490a9d1985bdaf",
  "repo_slug": "k1ta141k/mcp-bench-router",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_k1ta141k_mcp_bench_router_4055aee6/readme"
}