ado_mark_done · Google MCP: Risk & Policy

WHAT IT DOES

What ado_mark_done does on Google

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

WHY IT NEEDS A POLICY

Why ado_mark_done needs a policy

Marking a work item as Done is a Write operation—it changes the status field of a work item record, which is reversible (the item can be reopened or the status changed again). While it has project management implications, it does not delete data, execute arbitrary code, or trigger financial transactions.

From the tool's definition Tool name 'ado_mark_done' and description indicate it modifies work item state to 'Done' with completion notes and optional commit link. This is a state-changing operation that creates or modifies data reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ado_mark_done Rate-limited

ado_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": {
    "ado_mark_done": {
      "limits": [
        {
          "counter": "ado_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 Google, so you can run agents against it safely.

FAQ

Questions about ado_mark_done

What does the ado_mark_done tool do? +

Mark a work item as Done with completion notes and optional commit link. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ado_mark_done? +

Register the Google MCP server in PolicyLayer and add a rule for ado_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 Google. Nothing to install.

What risk level is ado_mark_done? +

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

Can I rate-limit ado_mark_done? +

Yes. Add a rate_limit block to the ado_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 ado_mark_done completely? +

Set action: deny in the PolicyLayer policy for ado_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 ado_mark_done? +

ado_mark_done is provided by the Google MCP server (psckeithw/mcp-google). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.