Enables AI agents to investigate and repair Python/pytest repositories in isolated Git worktrees with audit trails, without modifying the original repository.
Enables maintainers to batch-triage local Issue JSON, optionally invoke the Jev model, and calibrate plus held-out evaluate a policy that gates which predictions may be auto-accepted versus sent to human review. Also supports task and usage checks with call limits, without editing issues, applying labels, or posting comments.
This MCP server enables automated maintenance and code analysis for Python/pytest repositories in isolated Docker environments. It supports read-only investigations, fix-and-verify tasks, and provides full audit trails with SQLite event history and artifact exports.