mark_task_completed · Dag Planner MCP: Risk & Policy

WHAT IT DOES

What mark_task_completed does on Dag Planner

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

WHY IT NEEDS A POLICY

Why mark_task_completed needs a policy

This tool modifies task state durably within the DAG planner (marking completion status) and cascades effects through the dependency graph (activating dependent tasks). These are state changes, not data retrieval (Read), not code execution (Execute), and not irreversible deletion (Destructive).

From the tool's definition Tool name 'mark_task_completed' and description 'Mark a task completed and activate dependent tasks' indicates modification of task state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_task_completed Rate-limited

mark_task_completed 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_task_completed": {
      "limits": [
        {
          "counter": "mark_task_completed_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 Dag Planner, so you can run agents against it safely.

FAQ

Questions about mark_task_completed

What does the mark_task_completed tool do? +

Mark a task completed and activate dependent tasks. It is categorised as a Write tool in the Dag Planner 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_task_completed? +

Register the Dag Planner MCP server in PolicyLayer and add a rule for mark_task_completed: 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 Dag Planner. Nothing to install.

What risk level is mark_task_completed? +

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

Can I rate-limit mark_task_completed? +

Yes. Add a rate_limit block to the mark_task_completed 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_task_completed completely? +

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

mark_task_completed is provided by the Dag Planner MCP server (shubhamnegi/dag-planner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.