atp_complete_task · ATP Librarian MCP Server MCP

WHAT IT DOES

What atp_complete_task does on ATP Librarian MCP Server

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

WHY IT NEEDS A POLICY

Why atp_complete_task needs a policy

The tool creates or modifies data (task completion state) in a way that is reversible, placing it in the Write category rather than Destructive. However, severity is high because marking tasks as complete affects task dependency resolution and workflow progression—misuse could deadlock or corrupt the task graph state, impacting downstream tasks.

From the tool's definition Tool description states it 'Marks a node as DONE or FAILED and unlocks dependent tasks'. This modifies state (task status) and has cascading effects on dependent tasks, but the changes are reversible (a task can be re-opened or its state corrected).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

atp_complete_task Rate-limited

atp_complete_task 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": {
    "atp_complete_task": {
      "limits": [
        {
          "counter": "atp_complete_task_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 ATP Librarian MCP Server, so you can run agents against it safely.

FAQ

Questions about atp_complete_task

What does the atp_complete_task tool do? +

Marks a node as DONE or FAILED and unlocks dependent tasks. It is categorised as a Write tool in the ATP Librarian MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on atp_complete_task? +

Register the ATP Librarian MCP Server MCP server in PolicyLayer and add a rule for atp_complete_task: 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 ATP Librarian MCP Server. Nothing to install.

What risk level is atp_complete_task? +

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

Can I rate-limit atp_complete_task? +

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

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

atp_complete_task is provided by the ATP Librarian MCP Server MCP server (manuelcecchetto/atp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.