teammate_send_message · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What teammate_send_message does on Claude Flow

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

WHY IT NEEDS A POLICY

Why teammate_send_message needs a policy

This tool creates or modifies data (a message) within what appears to be an agent orchestration platform. It is reversible (messages can typically be deleted or edited) and produces side effects limited to communication/notification. It does not execute external code, delete data irreversibly, move money, or perform destructive actions.

From the tool's definition Tool name and description state it 'Send a message to a specific teammate' — the verb 'send' indicates creation of a message record in a messaging system, which is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

teammate_send_message Rate-limited

teammate_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": {
    "teammate_send_message": {
      "limits": [
        {
          "counter": "teammate_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about teammate_send_message

What does the teammate_send_message tool do? +

Send a message to a specific teammate. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on teammate_send_message? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for teammate_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 Claude Flow. Nothing to install.

What risk level is teammate_send_message? +

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

Can I rate-limit teammate_send_message? +

Yes. Add a rate_limit block to the teammate_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 teammate_send_message completely? +

Set action: deny in the PolicyLayer policy for teammate_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 teammate_send_message? +

teammate_send_message is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.