task_request_changes · Lockstep MCP: Risk & Policy

WHAT IT DOES

What task_request_changes does on Lockstep

AI agents use task_request_changes 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_request_changes needs a policy

This tool creates or modifies data reversibly by updating task status/workflow state. It does not execute arbitrary code, delete data irreversibly, or move money. The 'PLANNER ONLY' restriction suggests role-based access control. The medium severity reflects that misuse could disrupt workflow coordination but changes are reversible (the task can be moved forward again).

From the tool's definition Tool description states 'Request changes on a task in review, sending it back to in_progress' — this modifies the state of a task by transitioning it from 'review' status back to 'in_progress', which is a reversible state change to task metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_request_changes Rate-limited

task_request_changes 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_request_changes": {
      "limits": [
        {
          "counter": "task_request_changes_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_request_changes

What does the task_request_changes tool do? +

PLANNER ONLY: Request changes on a task in review, sending it back to in_progress. 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_request_changes? +

Register the Lockstep MCP server in PolicyLayer and add a rule for task_request_changes: 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_request_changes? +

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

Can I rate-limit task_request_changes? +

Yes. Add a rate_limit block to the task_request_changes 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_request_changes completely? +

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

task_request_changes 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.