What it does
The server takes a proposed action from an AI agent and compares it with the rules an operator has set. Each check returns one of three outcomes: permit, deny or escalate. The response also names the clause the decision is based on.
It fits setups where an agent's planned actions should be reviewed against written operator rules before they run. The publisher's description gives no further detail on setup or integration.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
ai.hanria/check
Check a proposed agent action against operator's rules: permit, deny or escalate, with the clause.
v0.2.0As shown on registry.modelcontextprotocol.io when we last read it