launch_implementer · Lockstep MCP: Risk & Policy

WHAT IT DOES

What launch_implementer does on Lockstep

AI agents invoke launch_implementer to trigger actions in Lockstep. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why launch_implementer needs a policy

This tool triggers the execution of external processes (agent launches in new terminal windows) whose behavior depends on the configuration provided (evidenced by the incomplete 'Set isolation=' parameter). While not destructive, this is clearly an Execute category tool as it spawns and controls independent computational processes.

From the tool's definition Tool description states it will 'Launch a new implementer agent (Claude or Codex) in a new terminal window' and that 'The planner uses this to spawn workers.' These phrases indicate execution of external agents/processes in a new terminal context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_implementer Rate-limited

launch_implementer stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "launch_implementer": {
      "limits": [
        {
          "counter": "launch_implementer_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 launch_implementer

What does the launch_implementer tool do? +

Launch a new implementer agent (Claude or Codex) in a new terminal window. The planner uses this to spawn workers. Set isolation=. It is categorised as a Execute tool in the Lockstep MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_implementer? +

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

launch_implementer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit launch_implementer? +

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

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

launch_implementer 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.