io.github.harshitAgr/codabench-mcp
MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.
Que pouvez-vous faire avec io.github.harshitAgr/codabench-mcp ?
search_competitions,get_competition,list_competition_phases,download_dataset(streaming + SHA-256)list_my_submissions,get_submission,get_submission_logssubmit_to_phase(handles Codabench's 3-step upload flow)poll_submission(backoff + timeout + non-error "still_running")get_leaderboard,get_my_profilecodabench_request— generic REST escape hatch (GET-only by default)
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
codabench-mcpclaude mcp add codabench-mcp -e 'CODABENCH_API_TOKEN=<your codabench_api_token>' -- uvx codabench-mcp==0.1.1
{
"mcpServers": {
"codabench-mcp": {
"command": "uvx",
"args": [
"codabench-mcp==0.1.1"
],
"env": {
"CODABENCH_API_TOKEN": "<your codabench_api_token>"
}
}
}
}
Variables d'environnement
CODABENCH_API_TOKENobligatoire secret DRF token for Codabench. Obtain via https://www.codabench.org/api/docs/ > api-token-auth > Try it out.
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
codabench-mcp
MCP server for the Codabench REST API. Lets an AI agent drive a full participant ML-benchmark workflow: discover competitions, read rules, download data, submit, poll, read leaderboards.
Features
Curated tools for the participant path:
search_competitions,get_competition,list_competition_phases,get_phase,get_competition_rules,list_competition_tasks,get_taskdownload_dataset(streaming + SHA-256)list_my_submissions,get_submission,get_submission_logssubmit_to_phase(handles Codabench's 3-step upload flow)poll_submission(backoff + timeout + non-error "still_running")get_leaderboard,get_my_profilecodabench_request— generic REST escape hatch (GET-only by default)
Authentication
You need a Codabench API token. Two ways to get one:
1. Swagger UI (recommended)
- Visit https://www.codabench.org/api/docs/
- Find the
api-token-authendpoint → Try it out - POST your username/password
- Copy the
tokenvalue from the response
2. curl
curl -X POST https://www.codabench.org/api/api-token-auth/ \
-H "Content-Type: application/json" \
-d '{"username":"YOUR_USERNAME","password":"YOUR_PASSWORD"}'
The response is {"token": "..."}.
Install
uvx codabench-mcp
To run the bleeding-edge main branch instead of the last release:
uvx --from git+https://github.com/harshitAgr/codabench-mcp codabench-mcp
Or for development:
git clone https://github.com/harshitAgr/codabench-mcp.git
cd codabench-mcp
uv sync
uv run codabench-mcp # requires CODABENCH_API_TOKEN
Configure an MCP client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"codabench": {
"command": "uvx",
"args": ["codabench-mcp"],
"env": {
"CODABENCH_API_TOKEN": "paste-your-token-here"
}
}
}
}
Claude Code (plugin marketplace)
/plugin marketplace add harshitAgr/codabench-mcp
/plugin install codabench-mcp@codabench-mcp
Then export your token in the shell where you launch Claude Code:
export CODABENCH_API_TOKEN=paste-your-token-here
Claude Code (manual)
If you'd rather skip the plugin layer:
claude mcp add codabench \
--env CODABENCH_API_TOKEN=paste-your-token-here \
-- uvx codabench-mcp
Environment variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
CODABENCH_API_TOKEN | yes | — | DRF token, sent as Authorization: Token <token> |
CODABENCH_BASE_URL | no | https://www.codabench.org | Override for tests |
CODABENCH_ALLOW_WRITE_RAW | no | 0 | Set to 1 to allow non-GET methods through codabench_request |
CODABENCH_MAX_DOWNLOAD_BYTES | no | 5368709120 (5 GB) | Cap for download_dataset |
Development
uv sync
uv run pytest # unit tests, no network
uv run ruff check . # lint
uv run ruff format --check . # format check
License
MIT — see LICENSE.
mcp-name: io.github.harshitAgr/codabench-mcp
Questions fréquentes
Qu'est-ce que io.github.harshitAgr/codabench-mcp ?
MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.
Comment installer io.github.harshitAgr/codabench-mcp ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add codabench-mcp -e 'CODABENCH_API_TOKEN=<your codabench_api_token>' -- uvx codabench-mcp==0.1.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour io.github.harshitAgr/codabench-mcp ?
Oui. Il attend CODABENCH_API_TOKEN, à renseigner dans sa configuration.
io.github.harshitAgr/codabench-mcp est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient io.github.harshitAgr/codabench-mcp ?
Il est publié par harshitAgr. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.