MCP.so
ログイン

OpenML MCP Server

@mallochio

OpenML MCP Server について

An MCP server to interact with OpenML

基本情報

カテゴリ

その他

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

mallochio

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "openml-mcp-server": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is OpenML MCP Server?

An MCP (Model Context Protocol) server that allows clients (like Claude Desktop) to interact with the public OpenML API. It exposes various OpenML API endpoints as MCP tools, enabling queries for datasets, tasks, flows, runs, and more directly from within an MCP-compatible client.

How to use OpenML MCP Server?

Install the uv Python package installer, then edit your Claude Desktop configuration (claude_desktop_config.json) to add the server with the command uv run openml-mcp-server and set the OPENML_API_KEY environment variable. After saving and restarting Claude Desktop, the tools become available under the hammer icon. For developers, clone the repository and run uv sync to install dependencies.

Key features of OpenML MCP Server

  • Provides MCP tools corresponding to major OpenML GET endpoints.
  • Query datasets, tasks, flows, runs, evaluations, setups, studies.
  • List entities with filtering capabilities where supported by the API.
  • Built using the mcp Python SDK (FastMCP).
  • Can be run with uv without explicit installation for end users.

Use cases of OpenML MCP Server

  • Show the description for an OpenML dataset by ID.
  • List features for a specific dataset from OpenML.
  • Find classification tasks on OpenML with filtering.
  • Get the run description for a given run ID.

FAQ from OpenML MCP Server

What tools does OpenML MCP Server provide?

It provides tools corresponding to major OpenML GET endpoints, such as get_dataset_description, list_tasks, list_runs, list_flows, and others for querying datasets, tasks, flows, runs, evaluations, setups, and studies.

Do I need an OpenML API key?

Yes, you must set the OPENML_API_KEY environment variable in the server configuration for the server to authenticate with the OpenML API.

How do I configure OpenML MCP Server with Claude Desktop?

Edit claude_desktop_config.json to add a server entry under mcpServers with the command "uv" and args ["run", "openml-mcp-server"], and include the OPENML_API_KEY in the env object.

What are some example queries I can make?

Example queries include "Show the description for OpenML dataset ID 61", "List features for dataset 31", "Find the first 3 classification tasks on OpenML", and "Get the run description for run ID 100."

Is OpenML MCP Server open source?

Yes, it is licensed under the MIT License.

コメント

「その他」の他のコンテンツ