kunobi_launch · Kunobi MCP Server MCP: Risk & Policy

WHAT IT DOES

What kunobi_launch does on Kunobi MCP Server

AI agents invoke kunobi_launch to trigger actions in Kunobi MCP Server. 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 kunobi_launch needs a policy

This tool triggers execution of an external application (Kunobi desktop app), which is a form of external operation execution. The effects are not fully predictable or reversible depending on what the app does upon launch. This falls under Execute category rather than Write because it invokes a separate process/application rather than creating/modifying data directly.

From the tool's definition Tool description: 'Launch the Kunobi desktop app.' The verb 'Launch' combined with 'desktop app' indicates execution of an external application, whose effects depend on runtime state and arguments (e.g., variant parameter).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kunobi_launch Rate-limited

kunobi_launch 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": {
    "kunobi_launch": {
      "limits": [
        {
          "counter": "kunobi_launch_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 Kunobi MCP Server, so you can run agents against it safely.

FAQ

Questions about kunobi_launch

What does the kunobi_launch tool do? +

Launch the Kunobi desktop app. Optionally specify a variant (e.g. It is categorised as a Execute tool in the Kunobi MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on kunobi_launch? +

Register the Kunobi MCP Server MCP server in PolicyLayer and add a rule for kunobi_launch: 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 Kunobi MCP Server. Nothing to install.

What risk level is kunobi_launch? +

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

Can I rate-limit kunobi_launch? +

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

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

kunobi_launch is provided by the Kunobi MCP Server MCP server (kunobi-ninja/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.