reply_message · MCP Agent Mail MCP: Risk & Policy

WHAT IT DOES

What reply_message does on MCP Agent Mail

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

WHY IT NEEDS A POLICY

Why reply_message needs a policy

Based on the tool name and server context (message threading and coordination), 'reply_message' most likely creates a new reply/message in a thread, which is a reversible write operation. The empty description lowers confidence, but sibling tools like 'acknowledge_message' and 'fetch_inbox' confirm this is a messaging system where replies would constitute Write actions.

From the tool's definition Tool name 'reply_message' in a messaging coordination server context; description is empty

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reply_message Rate-limited

reply_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": {
    "reply_message": {
      "limits": [
        {
          "counter": "reply_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 Agent Mail, so you can run agents against it safely.

FAQ

Questions about reply_message

What does the reply_message tool do? +

reply_message. It is categorised as a Write tool in the MCP Agent Mail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reply_message? +

Register the MCP Agent Mail MCP server in PolicyLayer and add a rule for reply_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 Agent Mail. Nothing to install.

What risk level is reply_message? +

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

Can I rate-limit reply_message? +

Yes. Add a rate_limit block to the reply_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 reply_message completely? +

Set action: deny in the PolicyLayer policy for reply_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 reply_message? +

reply_message is provided by the MCP Agent Mail MCP server (omelchmichael/mcp_agent_mail). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.