task_claim · Lockstep MCP: Risk & Policy

WHAT IT DOES

What task_claim does on Lockstep

AI agents use task_claim 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_claim needs a policy

The tool modifies task metadata (status field) in a shared coordination system. While reversible (status can be changed again), it affects workflow state that other agents depend on. This is a Write operation rather than Execute because it doesn't run arbitrary code or trigger external operations—it only updates a task record.

From the tool's definition Tool description states 'set status to in_progress', which modifies task state. This is a state-changing operation on shared project data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_claim Rate-limited

task_claim 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_claim": {
      "limits": [
        {
          "counter": "task_claim_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_claim

What does the task_claim tool do? +

Claim a task and set status 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_claim? +

Register the Lockstep MCP server in PolicyLayer and add a rule for task_claim: 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_claim? +

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

Can I rate-limit task_claim? +

Yes. Add a rate_limit block to the task_claim 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_claim completely? +

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

task_claim 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.