data-ai MCP Server
Native macOS system cleaner with YAML-driven safety rules, local AI explainability via MLX, and an MCP server for agent-controlled cleanup workflows.
Discovered via github-topic:model-context-protocol and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Disposable files that are expected to regenerate or have no user-owned state.
Meaning
Files that may be removable, but could contain preferences, sync state, offline data, or context the user should inspect.
Files with system impact, privilege implications, or high risk of data loss.
is required.
explain a filesystem path or prior scan item
item IDs are rejected.
dry-run scan for reclaimable items
MCP client gets one clean operation per 60 seconds.
clean item IDs returned by a prior `scan`
list built-in and custom cleanup profiles
`protected` item aborts the whole request.
current system health metrics
app attempts a local notification with a short cancel window before files move.
health score, disk usage, and recommendations
non-dry-run attempt writes an audit entry with the client identifier to `~/Library/Logs/Gargantua/audit.json`.