mark_task_done

THE RISK

Medium Risk

Why mark_task_done needs a policy

This tool modifies task metadata (completion status) reversibly—a task marked done could potentially be reopened or its status changed back. This is characteristic of Write operations (create, update, modify). It is not Execute because it doesn't run external code; not Destructive because completion status is reversible; not Read because it has side effects.

From the tool's definition Tool name 'mark_task_done' and description 'Mark a task as completed' indicate modification of task state. The sibling tools include both 'approve_task_completion' and 'delete_task', suggesting this tool changes task status rather than deleting it.

Documented attack patterns abuse exactly the kind of access mark_task_done gives an agent:

POLICY

How to control mark_task_done

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP TaskManager, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_task_done:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_task_done": {
      "limits": [
        {
          "counter": "mark_task_done_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mark_task_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.

Create a free account and register MCP TaskManager — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP TaskManager tools

Destructive delete_task Delete a task from a request. Write add_tasks_to_request Add new tasks to an existing request. Write approve_request_completion Approve the completion of an entire request. Write approve_task_completion Approve a completed task. Write request_planning Register a new user request and plan its associated tasks. Write update_task Update an existing task. Read get_next_task Get the next pending task for a request. Read list_requests List all requests in the system.

All 10 MCP TaskManager tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about mark_task_done

What does the mark_task_done tool do? +

Mark a task as completed. It is categorised as a Write tool in the MCP TaskManager 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_done? +

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

What risk level is mark_task_done? +

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

Can I rate-limit mark_task_done? +

Yes. Add a rate_limit block to the mark_task_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_task_done completely? +

Set action: deny in the PolicyLayer policy for mark_task_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_task_done? +

mark_task_done is provided by the MCP TaskManager MCP server (rudra-ravi/mcp-taskmanager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP TaskManager tool call.

Start from MCP TaskManager, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →