playidea-lab/pcq

Agent-operable ML experiment contract (cq.yaml + JSON contracts) with a built-in MCP server exposing 14 tools (resolve/inspect/run/validate/describe/compare/lineage) for running, validating, and tracing experiments across any framework (PyTorch / HF Trainer / Lightning / sklearn / XGBoost). Apache-2.0.

Quality score 41/100

View on GitHub →

Stars

★ 1

Last commit

2mo ago

Language

Python

Install

Python (uvx / pip)

Installation

Example client config (verify package name in the repo README)

{
  "mcpServers": {
    "pcq": {
      "command": "uvx",
      "args": ["pcq"]
    }
  }
}

Related in Data Science Tools

MCP Server Official Active

mckinsey/vizro-mcp

Tools and templates to create validated and maintainable data charts and dashboards.

★ 3.8k Python Updated today Score 96

Data Science Tools

MCP Server Official Active

DataEval/dingo

MCP server for the Dingo: a comprehensive data quality evaluation tool. Server Enables interaction with Dingo's rule-based and LLM-based evaluation capabilities and rules&prompts listing.

★ 731 Python Updated yesterday Score 89

Data Science Tools

MCP Server Active