# codabench-mcp

> Use this tool when you need to automate machine learning benchmark workflows, enabling AI agents to discover competitions, download data, submit models, and track performance on leaderboards. It solves problems of manual workflow management and provides a seamless interface for AI agents to interact with machine learning competitions. The codabench-mcp server accepts API requests and returns relevant data, such as competition information, submission results, and leaderboard rankings.

Canonical page: https://skillsregistry.net/skills/harshitagr-codabench-mcp  
JSON: https://api.skillsregistry.net/v1/skills/harshitagr-codabench-mcp

## Description

MCP server for Codabench REST API that enables AI agents to drive a full participant ML-benchmark workflow: discover competitions, download data, submit, poll, and read leaderboards.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-26

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gwaa02tnei)
- **Repository:** <https://github.com/harshitAgr/codabench-mcp>

## 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": "harshitagr-codabench-mcp"
    }
  }
}
```

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