guard_action · Maple MCP: Risk & Policy

WHAT IT DOES

What guard_action does on Maple

AI agents invoke guard_action to trigger actions in Maple. 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 guard_action needs a policy

This tool actively controls agent execution flow by approving or blocking actions, and can quarantine traces. It triggers external control operations whose effects depend on arguments (approve/block/pending), making it an Execute-category tool. The blast radius is high because a misconfigured block could halt legitimate agent operations, or a misconfigured approval could allow dangerous actions to proceed.

From the tool's definition 'Approve, block, or set pending state for a specific risky step. Blocking quarantines the trace.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

guard_action Rate-limited

guard_action 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": {
    "guard_action": {
      "limits": [
        {
          "counter": "guard_action_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 Maple, so you can run agents against it safely.

FAQ

Questions about guard_action

What does the guard_action tool do? +

Approve, block, or set pending state for a specific risky step. Blocking quarantines the trace. It is categorised as a Execute tool in the Maple MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on guard_action? +

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

What risk level is guard_action? +

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

Can I rate-limit guard_action? +

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

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

guard_action is provided by the Maple MCP server (omar2001ramadan/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.