openml-mcp-server
If you are the rightful owner of openml-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server that allows clients to interact with the OpenML API.
The OpenML MCP Server is a Model Context Protocol server designed to facilitate interaction with the OpenML API through MCP-compatible clients like Claude Desktop. It provides a seamless way to query and retrieve data from OpenML, including datasets, tasks, flows, runs, and more. The server is built using the `mcp` Python SDK, specifically `FastMCP`, and exposes various OpenML API endpoints as MCP tools. This allows users to perform complex queries and data retrieval operations directly from their MCP client interface. The server is open-source and licensed under the MIT License, making it accessible for both end-users and developers who wish to contribute or customize the server for their specific needs.
Features
- 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`).
Tools
get_dataset_description
Retrieve the description of a specific dataset by ID.
list_tasks
List available tasks with optional filtering.
get_run_description
Get the description of a specific run by ID.
