mark_task_failed · Dag Planner MCP: Risk & Policy

WHAT IT DOES

What mark_task_failed does on Dag Planner

AI agents use mark_task_failed 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_failed needs a policy

This tool modifies task metadata and state within the DAG planner without destroying data or executing external code. It falls under Write category because it creates or modifies data reversibly. Severity is high because misuse could corrupt workflow state, cause cascading failures in dependent tasks, or trigger unwanted retries that waste resources or cause side effects in external systems.

From the tool's definition Tool name 'mark_task_failed' and description 'Mark a task failed, with optional retry logic' indicate modification of task state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_task_failed Rate-limited

mark_task_failed 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_failed": {
      "limits": [
        {
          "counter": "mark_task_failed_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_failed

What does the mark_task_failed tool do? +

Mark a task failed, with optional retry logic. 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_failed? +

Register the Dag Planner MCP server in PolicyLayer and add a rule for mark_task_failed: 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_failed? +

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

Can I rate-limit mark_task_failed? +

Yes. Add a rate_limit block to the mark_task_failed 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_failed completely? +

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

mark_task_failed 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.