mark_done · Codecks MCP: Risk & Policy

WHAT IT DOES

What mark_done does on Codecks

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

WHY IT NEEDS A POLICY

Why mark_done needs a policy

The tool modifies card state by marking them as complete/done, which changes data in the Codecks system. This is reversible (cards can be reopened), so it falls under Write rather than Destructive. The blast radius is medium—an agent could mark many cards as done incorrectly, disrupting project tracking, but the action can be undone.

From the tool's definition Tool name 'mark_done' and description 'Mark cards as done' indicates a state-change operation that modifies card status within the project management system. This is a reversible write operation (cards can typically be unmarked or reopened in PM tools).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_done Rate-limited

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": {
    "mark_done": {
      "limits": [
        {
          "counter": "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 Codecks, so you can run agents against it safely.

FAQ

Questions about mark_done

What does the mark_done tool do? +

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

How do I enforce a policy on mark_done? +

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

What risk level is mark_done? +

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

Can I rate-limit mark_done? +

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

Set action: deny in the PolicyLayer policy for 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 mark_done? +

mark_done is provided by the Codecks MCP server (rangogamedev/codecks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.