leave_channel · MCP channel MCP: Risk & Policy

WHAT IT DOES

What leave_channel does on MCP channel

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

WHY IT NEEDS A POLICY

Why leave_channel needs a policy

This tool creates or modifies communication state reversibly rather than executing external operations or deleting data irreversibly. Leaving a channel updates the agent's membership status but does not destroy data, execute code, or move money. The blast radius is minimal—worst case is an agent leaves a channel it shouldn't, requiring it to rejoin.

From the tool's definition Tool performs 'leave_channel' which modifies membership state by removing the agent from a previously joined channel. This is a reversible state change (the agent can rejoin the channel).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

leave_channel Rate-limited

leave_channel 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": {
    "leave_channel": {
      "limits": [
        {
          "counter": "leave_channel_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP channel, so you can run agents against it safely.

FAQ

Questions about leave_channel

What does the leave_channel tool do? +

Leave a channel you previously joined. It is categorised as a Write tool in the MCP channel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on leave_channel? +

Register the MCP channel MCP server in PolicyLayer and add a rule for leave_channel: 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 MCP channel. Nothing to install.

What risk level is leave_channel? +

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

Can I rate-limit leave_channel? +

Yes. Add a rate_limit block to the leave_channel 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 leave_channel completely? +

Set action: deny in the PolicyLayer policy for leave_channel. 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 leave_channel? +

leave_channel is provided by the MCP channel MCP server (rmarquis/mcp-channel). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.