crow_room_close

Close an active companion room. Invalidates the room token and optionally notifies participants.

SERVERCrow SOURCEkh0pper/crow

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/kh0pper-crow/crow-room-close.md

WHAT IT DOES

What crow_room_close does on Crow

AI agents use crow_room_close to create or update resources in Crow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.

RISK

Why crow_room_close is rated Medium

This tool modifies data (room state, token validity) and affects an active system, but does not permanently delete underlying data or resources. Closing a room is reversible through reopening/recreation. The blast radius is moderate—it disrupts current participants but doesn't cause permanent data loss or financial harm.

From the tool's definition Tool description: 'Close an active companion room. Invalidates the room token and optionally notifies participants.' - the action of closing a room and invalidating its token modifies the state of an active collaboration session.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs crow_room_close safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crow_room_close, this is the rule to start with:

crow_room_close Rate-limited

crow_room_close stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "crow_room_close": {
      "limits": [
        {
          "counter": "crow_room_close_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_room_close call is checked against it from then on.

FAQ

Questions about crow_room_close

What does the crow_room_close tool do? +

Close an active companion room. Invalidates the room token and optionally notifies participants. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on crow_room_close? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_room_close: 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.

What risk level is crow_room_close? +

crow_room_close is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit crow_room_close? +

Yes. Add a rate_limit block to the crow_room_close 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.

How do I block crow_room_close completely? +

Set action: deny in the PolicyLayer policy for crow_room_close. 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.

What MCP server provides crow_room_close? +

crow_room_close 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.

KEEP EXPLORING

More on Crow, and thousands of servers like it.

This server

All 587 Crow tools →

Across the catalogue

team_manager_plan_room on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →