report_directive · AT MCP: Risk & Policy

WHAT IT DOES

What report_directive does on ATMcp

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

WHY IT NEEDS A POLICY

Why report_directive needs a policy

This tool creates or modifies data (directive status) reversibly. It updates an existing directive's completion status rather than executing external operations or deleting data. While this could affect downstream task coordination in a multi-agent system, the operation is reversible (status can potentially be corrected) and the blast radius is limited to workflow state management.

From the tool's definition Tool name 'report_directive' and description 'Report a directive finished: status must be \'done\' or \'failed\'' indicates it modifies the state of a directive by updating its status field to a terminal state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_directive Rate-limited

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

FAQ

Questions about report_directive

What does the report_directive tool do? +

Report a directive finished: status must be 'done' or 'failed'. The issuer's. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_directive? +

Register the AT MCP server in PolicyLayer and add a rule for report_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 report_directive? +

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

Can I rate-limit report_directive? +

Yes. Add a rate_limit block to the report_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 report_directive completely? +

Set action: deny in the PolicyLayer policy for report_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 report_directive? +

report_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.