task_approve_batch · Lockstep MCP: Risk & Policy

WHAT IT DOES

What task_approve_batch does on Lockstep

AI agents use task_approve_batch 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_batch needs a policy

Approving tasks modifies their state in a shared project coordination system, making this a Write operation. The ability to batch-approve affects multiple agents' work pipelines, elevating severity to medium due to potential workflow disruption if misused (e.g., approving inappropriate tasks that then propagate to other agents).

From the tool's definition Tool description states 'Approve multiple tasks at once', indicating modification of task state/status. The 'PLANNER ONLY' restriction suggests privileged write operations that affect coordination state across multiple agents.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_approve_batch Rate-limited

task_approve_batch 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_batch": {
      "limits": [
        {
          "counter": "task_approve_batch_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_batch

What does the task_approve_batch tool do? +

PLANNER ONLY: Approve multiple tasks at once. More efficient than approving one by one. 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_batch? +

Register the Lockstep MCP server in PolicyLayer and add a rule for task_approve_batch: 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_batch? +

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

Can I rate-limit task_approve_batch? +

Yes. Add a rate_limit block to the task_approve_batch 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_batch completely? +

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

task_approve_batch 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.