completeTask · Trellis MCP: Risk & Policy

WHAT IT DOES

What completeTask does on Trellis MCP

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

WHY IT NEEDS A POLICY

Why completeTask needs a policy

The tool completes (marks as done) a task in a hierarchical project management system. Completing a task modifies the state of stored project data reversibly—the status change can be undone by reopening or resetting the task. This is a Write operation (modification of data state) rather than Destructive (since task completion is not permanent deletion and can be reverted).

From the tool's definition Tool name is 'completeTask' and server supports creating, claiming, and completing tasks with Markdown-based storage. The tool description is empty, limiting direct evidence.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

completeTask Rate-limited

completeTask 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": {
    "completeTask": {
      "limits": [
        {
          "counter": "completetask_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 Trellis MCP, so you can run agents against it safely.

FAQ

Questions about completeTask

What does the completeTask tool do? +

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

How do I enforce a policy on completeTask? +

Register the Trellis MCP server in PolicyLayer and add a rule for completeTask: 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 Trellis MCP. Nothing to install.

What risk level is completeTask? +

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

Can I rate-limit completeTask? +

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

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

completeTask is provided by the Trellis MCP server (langadventurellc/trellis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.