send_message · MCP channel MCP: Risk & Policy

WHAT IT DOES

What send_message does on MCP channel

AI agents use send_message 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 send_message needs a policy

send_message creates new data (messages) in a communication system. It is reversible (messages can typically be deleted or ignored by recipients) and has no direct destructive or financial impact. While it enables inter-agent communication that could be misused for prompt injection or social engineering between agents, the tool itself only writes messages.

From the tool's definition Tool description states it 'Send a message to another Claude session (by name or ID) or to a channel.' The verb 'send' with 'message' indicates creation/modification of communication data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_message Rate-limited

send_message 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": {
    "send_message": {
      "limits": [
        {
          "counter": "send_message_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 send_message

What does the send_message tool do? +

Send a message to another Claude session (by name or ID) or to a channel. 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 send_message? +

Register the MCP channel MCP server in PolicyLayer and add a rule for send_message: 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 send_message? +

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

Can I rate-limit send_message? +

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

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

send_message 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.