complete · Proofhub MCP: Risk & Policy

WHAT IT DOES

What complete does on Proofhub

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

WHY IT NEEDS A POLICY

Why complete needs a policy

This tool modifies task data by changing its completion status. While the change is reversible (a task can typically be unmarked as complete), it is still a mutative operation that alters persistent state. This falls under Write rather than Execute because it performs a specific, bounded data modification rather than arbitrary code execution.

From the tool's definition Tool description explicitly states 'Mark a task complete', which modifies the state of a task from incomplete to complete.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete Rate-limited

complete 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": {
    "complete": {
      "limits": [
        {
          "counter": "complete_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 Proofhub, so you can run agents against it safely.

FAQ

Questions about complete

What does the complete tool do? +

Mark a task complete (resolves the internal id automatically). project and todolist default to context. It is categorised as a Write tool in the Proofhub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on complete? +

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

What risk level is complete? +

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

Can I rate-limit complete? +

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

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

complete is provided by the Proofhub MCP server (yashmody/proofhub-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.