# Codabench

> Use this tool when you need to manage machine learning competition submissions, retrieve leaderboard results, or interact with benchmark datasets. Codabench solves problems related to ML model evaluation and comparison through its REST API, enabling automated workflows and integration with AI systems. It requires a Codabench API token for authentication and provides a programmatic interface for AI assistants to participate in ML benchmarks.

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

## Description

Codabench drives the full ML benchmark participant workflow through the Codabench REST API. It enables AI assistants to manage competition submissions, retrieve leaderboard results, and interact with benchmark datasets on the Codabench platform. The server requires a Codabench API token for authentication.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/harshitagr-codabench)
- **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"
    }
  }
}
```

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