codeloop_run_history
Query past CodeLoop runs for this project. Supports filtering by tool, status, and time range.
When to use codeloop_run_history
Use `codeloop_run_history` when your AI agent needs to query past codeloop runs for this project. supports filtering by tool, status, and time range.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| limit | number | no (default: 20) | Max number of runs to return. |
| tool | string | no | Filter to runs that invoked a specific tool. |
| project_dir | string | no | Project root. |
What you get back
Array of run summaries: { run_id, started_at, tool, status, artifact_paths }.
FAQ
What does codeloop_run_history do?
Query past CodeLoop runs for this project. Supports filtering by tool, status, and time range.
When should an AI agent call codeloop_run_history?
Use `codeloop_run_history` when your AI agent needs to query past codeloop runs for this project. supports filtering by tool, status, and time range.
What does codeloop_run_history return?
Array of run summaries: { run_id, started_at, tool, status, artifact_paths }.
Is codeloop_run_history part of the CodeLoop MCP server?
Yes. CodeLoop ships as an MCP server installed via `npx codeloop init`. Cursor and Claude Code call it automatically once the User Rule (Cursor) or CLAUDE.md (Claude Code) is in place.