msg_send_proposal · Agent Messaging MCP: Risk & Policy

WHAT IT DOES

What msg_send_proposal does on Agent Messaging

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

WHY IT NEEDS A POLICY

Why msg_send_proposal needs a policy

This tool creates a new proposal message and sends it to another agent, modifying the state of the messaging system by adding a new structured message. This is reversible (the proposal can be ignored, rejected, or withdrawn in typical messaging systems) and has no destructive, financial, or code-execution side effects.

From the tool's definition Tool name 'msg_send_proposal' and description 'Send a structured work proposal to another agent' indicate creation of new message content. The verb 'send' paired with 'proposal' shows the tool creates and transmits data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

msg_send_proposal Rate-limited

msg_send_proposal 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": {
    "msg_send_proposal": {
      "limits": [
        {
          "counter": "msg_send_proposal_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 Agent Messaging, so you can run agents against it safely.

FAQ

Questions about msg_send_proposal

What does the msg_send_proposal tool do? +

Send a structured work proposal to another agent. It is categorised as a Write tool in the Agent Messaging MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on msg_send_proposal? +

Register the Agent Messaging MCP server in PolicyLayer and add a rule for msg_send_proposal: 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 Agent Messaging. Nothing to install.

What risk level is msg_send_proposal? +

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

Can I rate-limit msg_send_proposal? +

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

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

msg_send_proposal is provided by the Agent Messaging MCP server (rumblingb/agent-messaging-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.