create_message · Imap MCP: Risk & Policy

WHAT IT DOES

What create_message does on Imap

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

WHY IT NEEDS A POLICY

Why create_message needs a policy

Creating messages (drafts) in an email system is a write operation—it creates new data (email drafts) that can be sent or further modified. While reversible (drafts can be deleted), it modifies the mailbox state and could be misused to create malicious emails, spam, phishing attempts, or impersonate the account holder.

From the tool's definition Tool is named 'create_message' on an IMAP server that enables 'draft creation' per server description. The server description explicitly mentions draft creation capability, and this tool name directly corresponds to that function.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_message Rate-limited

create_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": {
    "create_message": {
      "limits": [
        {
          "counter": "create_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 Imap, so you can run agents against it safely.

FAQ

Questions about create_message

What does the create_message tool do? +

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

How do I enforce a policy on create_message? +

Register the Imap MCP server in PolicyLayer and add a rule for create_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 Imap. Nothing to install.

What risk level is create_message? +

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

Can I rate-limit create_message? +

Yes. Add a rate_limit block to the create_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 create_message completely? +

Set action: deny in the PolicyLayer policy for create_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 create_message? +

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