maid_snapshot · Maid Runner MCP: Risk & Policy

WHAT IT DOES

What maid_snapshot does on Maid Runner

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

WHY IT NEEDS A POLICY

Why maid_snapshot needs a policy

Based on the tool name and server context (MAID Runner with 'snapshot' validation tools), this tool likely captures a system snapshot - a point-in-time capture that creates/writes data. The sibling tool 'maid_snapshot_system' reinforces this interpretation. However, the empty description significantly reduces confidence.

From the tool's definition Tool name 'maid_snapshot' and sibling tool 'maid_snapshot_system' suggest snapshot/capture functionality; description is empty

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

maid_snapshot Rate-limited

maid_snapshot 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": {
    "maid_snapshot": {
      "limits": [
        {
          "counter": "maid_snapshot_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 Maid Runner, so you can run agents against it safely.

FAQ

Questions about maid_snapshot

What does the maid_snapshot tool do? +

maid_snapshot. It is categorised as a Write tool in the Maid Runner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on maid_snapshot? +

Register the Maid Runner MCP server in PolicyLayer and add a rule for maid_snapshot: 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 Maid Runner. Nothing to install.

What risk level is maid_snapshot? +

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

Can I rate-limit maid_snapshot? +

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

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

maid_snapshot is provided by the Maid Runner MCP server (mamertofabian/maid-runner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.