Run agentic anomaly investigations with PyOD
Use PyOD's agent skill or MCP server to turn natural-language anomaly detection requests into repeatable detector selection, fitting, scoring, and investigation workflows.
Prerequisites
Python, pip, PyOD, optional MCP-compatible client
Installation
Use the upstream install or setup path that matches your environment:
- pip install pyod
- pip install pyod[mcp]
Requirements and caveats from upstream:
- Python Outlier Detection (PyOD) 3
- PyOD 3 is the most comprehensive Python library for anomaly detection. Four pillars:
2. Any MCP-compatible LLM — requires the optional mcp extra
Basic usage or getting-started notes:
^^^^^^^
Core library (required for every activation path):
.. code-block:: bash
Source: https://github.com/yzhao062/pyod
Extracted from upstream docs: https://raw.githubusercontent.com/yzhao062/pyod/HEAD/README.rst