append_output · AT MCP: Risk & Policy

WHAT IT DOES

What append_output does on ATMcp

AI agents use append_output 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 append_output needs a policy

This tool writes progress updates to a shared output/console stream, allowing other agents to observe real-time progress. It modifies data (appends to output) but does so reversibly and with no destructive or external effects. The blast radius is minimal—misuse results in spurious log messages rather than data loss or external consequences.

From the tool's definition 'Stream a chunk of YOUR output/progress' indicates the tool creates and appends new data to an output stream or log.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

append_output Rate-limited

append_output 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": {
    "append_output": {
      "limits": [
        {
          "counter": "append_output_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 append_output

What does the append_output tool do? +

Stream a chunk of YOUR output/progress so the console can watch it live (optionally. 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 append_output? +

Register the AT MCP server in PolicyLayer and add a rule for append_output: 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 append_output? +

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

Can I rate-limit append_output? +

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

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

append_output 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.