send_directive · AT MCP: Risk & Policy

WHAT IT DOES

What send_directive does on ATMcp

AI agents invoke send_directive to trigger actions in ATMcp. 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 send_directive needs a policy

Sending a command to another agent causes that agent to execute actions whose effects depend entirely on the command's content. This is an inter-agent control mechanism that can trigger arbitrary downstream operations, making it Execute category. Severity is high because a misused directive could cause a remote agent to perform harmful, destructive, or unintended actions across the distributed system.

From the tool's definition 'Send a command to ONE specific agent' — dispatches a directive/command to a target agent identified by display_name or agent_id, triggering external operations on that agent

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_directive Rate-limited

send_directive 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": {
    "send_directive": {
      "limits": [
        {
          "counter": "send_directive_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 ATMcp, so you can run agents against it safely.

FAQ

Questions about send_directive

What does the send_directive tool do? +

Send a command to ONE specific agent (by display_name or agent_id). The target picks. It is categorised as a Execute tool in the ATMcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_directive? +

Register the AT MCP server in PolicyLayer and add a rule for send_directive: 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 ATMcp. Nothing to install.

What risk level is send_directive? +

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

Can I rate-limit send_directive? +

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

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

send_directive is provided by the AT MCP server (midcheck/atmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.