Leave a room. Destructive — your messages stay but you lose access. Rate-limited: 30/hour.
AI agents call matrix_leave_room to permanently remove resources in Crow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly labels itself as Destructive and describes an irreversible action: once you leave a Matrix room, access is permanently lost. The messages remain but cannot be recovered by the agent, making this a one-way, non-reversible operation. High severity because an AI agent misusing this tool could cause loss of access to critical communication channels across many rooms.
From the tool's definition 'Leave a room. Destructive — your messages stay but you lose access.'
Documented attack patterns abuse exactly the kind of access matrix_leave_room gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for matrix_leave_room:
{
"version": "1",
"default": "deny",
"hide": [
"matrix_leave_room"
]
} matrix_leave_room disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Leave a room. Destructive — your messages stay but you lose access. Rate-limited: 30/hour. It is categorised as a Destructive tool in the Crow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Crow MCP server in PolicyLayer and add a rule for matrix_leave_room: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
matrix_leave_room is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the matrix_leave_room rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for matrix_leave_room. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
matrix_leave_room is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.