batch_mark_done · Amazing Marvin MCP: Risk & Policy

WHAT IT DOES

What batch_mark_done does on Amazing Marvin MCP

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

WHY IT NEEDS A POLICY

Why batch_mark_done needs a policy

This tool updates task completion status, which is a write operation that modifies data. It is reversible (tasks can be unmarked), so it does not qualify as Destructive. The moderate severity reflects the potential for an AI agent to incorrectly mark many tasks as complete, causing workflow disruption, though the impact is limited to status metadata and can be undone.

From the tool's definition Tool description states 'Mark multiple tasks as done at once' which performs a status update operation on multiple tasks. This modifies task state reversibly—tasks can be unmarked as done.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_mark_done Rate-limited

batch_mark_done 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": {
    "batch_mark_done": {
      "limits": [
        {
          "counter": "batch_mark_done_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 Amazing Marvin MCP, so you can run agents against it safely.

FAQ

Questions about batch_mark_done

What does the batch_mark_done tool do? +

Mark multiple tasks as done at once. It is categorised as a Write tool in the Amazing Marvin MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on batch_mark_done? +

Register the Amazing Marvin MCP server in PolicyLayer and add a rule for batch_mark_done: 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 Amazing Marvin MCP. Nothing to install.

What risk level is batch_mark_done? +

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

Can I rate-limit batch_mark_done? +

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

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

batch_mark_done is provided by the Amazing Marvin MCP server (qemqemqem/amazing-marvin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.