task_approve · Lockstep MCP: Risk & Policy

WHAT IT DOES

What task_approve does on Lockstep

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

WHY IT NEEDS A POLICY

Why task_approve needs a policy

This tool creates or modifies data (task status) in a reversible manner. While it has control-flow implications in a multi-agent coordination system, the action itself is a state update that could be undone (task can be re-opened or status changed again). It is not destructive (no deletion), not financial, and not code execution.

From the tool's definition The tool description states it 'Approve a task that is in review status, marking it done' — this modifies the state of a task from 'review' to 'done', which is a reversible state change to data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_approve Rate-limited

task_approve 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": {
    "task_approve": {
      "limits": [
        {
          "counter": "task_approve_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 Lockstep, so you can run agents against it safely.

FAQ

Questions about task_approve

What does the task_approve tool do? +

PLANNER ONLY: Approve a task that is in review status, marking it done. It is categorised as a Write tool in the Lockstep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on task_approve? +

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

What risk level is task_approve? +

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

Can I rate-limit task_approve? +

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

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

task_approve is provided by the Lockstep MCP server (tmmoore286/lockstep-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.