pilotgentic_messages_manager · PilotGentic MCP

WHAT IT DOES

What pilotgentic_messages_manager does on PilotGentic

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

WHY IT NEEDS A POLICY

Why pilotgentic_messages_manager needs a policy

The primary risk is the ability to send messages (iMessage/SMS) on behalf of the user without their real-time consent. This could be used to impersonate the user, send spam, phishing, or manipulative messages to contacts. The tool also permits reading and searching messages, but the Write category is more severe.

From the tool's definition Tool can 'send iMessage/SMS' which creates new messages and modifies the messaging state. Additional capabilities include 'get unread count', 'list chats', 'read messages', 'search messages', and 'open conversations'—these are Read operations, but the Send…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pilotgentic_messages_manager Rate-limited

pilotgentic_messages_manager 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": {
    "pilotgentic_messages_manager": {
      "limits": [
        {
          "counter": "pilotgentic_messages_manager_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 PilotGentic, so you can run agents against it safely.

FAQ

Questions about pilotgentic_messages_manager

What does the pilotgentic_messages_manager tool do? +

Manage macOS Messages.app: send iMessage/SMS, get unread count, list chats, read messages, search messages, open conversations. It is categorised as a Write tool in the PilotGentic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on pilotgentic_messages_manager? +

Register the PilotGentic MCP server in PolicyLayer and add a rule for pilotgentic_messages_manager: 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 PilotGentic. Nothing to install.

What risk level is pilotgentic_messages_manager? +

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

Can I rate-limit pilotgentic_messages_manager? +

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

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

pilotgentic_messages_manager is provided by the PilotGentic MCP server (@pilotgentic/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.