# mcp-tournament

> mcp-tournament — samalbanese-mcp-tournament. Use this tool when you need to evaluate and compare the performance of large language models (LLMs) through customizable benchmarks and multi-judge assessments. It solves the problem of objectively ranking LLMs by providing auditable results, supporting various interfaces including GUI, CLI, and MCP client. Ideal for use cases requiring transparent and reliable LLM evaluation, such as model selection and development.

Canonical page: https://skillsregistry.net/skills/samalbanese-mcp-tournament  
JSON: https://api.skillsregistry.net/v1/skills/samalbanese-mcp-tournament

## Description

Enables building and running custom LLM benchmarks with multi-judge evaluation, supporting GUI, MCP client, and CLI usage for ranked, auditable results.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/yho7c7jg26)
- **Repository:** <https://github.com/samalbanese/mcp-tournament>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "samalbanese-mcp-tournament"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/samalbanese-mcp-tournament` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/samalbanese-mcp-tournament/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt