# ManagerProtocol MCP server

> Provides a governance framework for AI agents including compliance enforcement, risk scoring, rate limiting, and human-in-the-loop approval workflows.

- Repository: https://github.com/TrentApps-com/ManagerProtocol
- Page: https://hostedmcp.org/servers/trentapps-com/managerprotocol
- Transport: —
- Stars: 2
- License: MIT

## Tools (38)

- `evaluate_action`
- `apply_business_rules`
- `require_human_approval`
- `log_event`
- `css_eval`
- `analyze_css_cleanup`
- `suggest_css_variables`
- `create_task`
- `get_tasks`
- `get_pending_tasks`
- `get_approved_tasks`
- `update_task`
- `close_task_with_comment`
- `add_task_comment`
- `link_commits`
- `add_monitored_app`
- `check_app_health`
- `check_all_apps_health`
- `get_app_status`
- `list_monitored_apps`
- `get_offline_apps`
- `register_session`
- `complete_session`
- `health_check`
- `list_rules`
- `add_rule`
- `remove_rule`
- `load_preset`
- `discover_relevant_rules`
- `list_project_profiles`
- `list_pending_approvals`
- `approve_request`
- `deny_request`
- `check_approval_status`
- `get_audit_events`
- `get_audit_stats`
- `export_audit_log`
- `get_approval_stats`

## FAQ

### What can Agent Supervisor do for my AI agents?

It provides compliance enforcement, action and rate limiting, risk scoring, comprehensive audits, human-in-the-loop approval workflows, and UX/Architecture validation.

### How does the human-in-the-loop approval work with Claude Code?

The best pattern is for Claude to use its AskUserQuestion tool after calling evaluate_action, which provides instant inline CLI prompts for the user to approve or deny.
