mcp-tournament

samalbanese/mcp-tournament
★ 0 stars TypeScript AI/LLM Updated today
Benchmark LLMs on your own scenarios: multi-judge panel scoring via one OpenRouter key. MCP server + local GUI + CLI + desktop app.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-tournament": {
      "command": "npx",
      "args": [
        "-y",
        "samalbanese/mcp-tournament"
      ]
    }
  }
}

README Excerpt

Build a custom LLM benchmark in a form, run it from a local GUI, MCP client, or CLI, and turn independent judge opinions into ranked, auditable results. **[▶ Live demo](https://mcp-tournament.pages.dev/#/replay/run-2026-07-18-194500)** — watch a real `business-strategy` run assemble itself, no key needed.

Tools (4)

OPENROUTER_API_KEYTOURNAMENT_RESULTS_DIRcodingdnd

Topics

benchmarkelectronllm-evaluationmcpmodel-context-protocolmulti-agentopenroutertypescript