session_message · Managed Agent Control MCP: Risk & Policy

WHAT IT DOES

What session_message does on Managed Agent Control

AI agents invoke session_message to trigger actions in Managed Agent Control. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why session_message needs a policy

This tool initiates or continues agent execution. While the message itself is input data, it directly triggers the agent to perform actions whose consequences depend on what instructions the message contains. An AI sending arbitrary messages to a managed agent could cause it to execute unintended operations, making this an Execute-class tool with high severity.

From the tool's definition Tool sends a user message to launch/continue agent work ('start work, reply, or continue a turn'), which triggers the agent to execute tasks whose effects depend on the message content and agent capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_message Rate-limited

session_message stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "session_message": {
      "limits": [
        {
          "counter": "session_message_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Managed Agent Control, so you can run agents against it safely.

FAQ

Questions about session_message

What does the session_message tool do? +

Send a user message to the agent — start work, reply, or continue a turn. It is categorised as a Execute tool in the Managed Agent Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on session_message? +

Register the Managed Agent Control MCP server in PolicyLayer and add a rule for session_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 Managed Agent Control. Nothing to install.

What risk level is session_message? +

session_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit session_message? +

Yes. Add a rate_limit block to the session_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 session_message completely? +

Set action: deny in the PolicyLayer policy for session_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 session_message? +

session_message is provided by the Managed Agent Control MCP server (modus-agendi/managed-agent-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.