launch_agent · Cursor Cloud Agent MCP: Risk & Policy

WHAT IT DOES

What launch_agent does on Cursor Cloud Agent

AI agents invoke launch_agent to trigger actions in Cursor Cloud Agent. 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_agent needs a policy

launch_agent triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_agent Rate-limited

launch_agent 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_agent": {
      "limits": [
        {
          "counter": "launch_agent_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 Cursor Cloud Agent, so you can run agents against it safely.

FAQ

Questions about launch_agent

What does the launch_agent tool do? +

Start a new cloud agent to work on your repository. It is categorised as a Execute tool in the Cursor Cloud Agent 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_agent? +

Register the Cursor Cloud Agent MCP server in PolicyLayer and add a rule for launch_agent: 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 Cursor Cloud Agent. Nothing to install.

What risk level is launch_agent? +

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

Can I rate-limit launch_agent? +

Yes. Add a rate_limit block to the launch_agent 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_agent completely? +

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

launch_agent is provided by the Cursor Cloud Agent MCP server (willpowell8/cursor-cloud-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.