juno_run · Junobuild MCP: Risk & Policy

WHAT IT DOES

What juno_run does on Junobuild

AI agents invoke juno_run to trigger actions in Junobuild. 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 juno_run needs a policy

This tool executes code (JavaScript/TypeScript) whose effects depend entirely on the script content provided as an argument. While the script runs in an authenticated Juno environment, the consequences are unpredictable and depend on what the agent chooses to execute. This is classic Execute behavior.

From the tool's definition Tool description states it can 'Run a custom JavaScript or TypeScript script in the CLI context' with 'access to the authenticated Juno environment.' Running arbitrary scripts is Execute category.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

juno_run Rate-limited

juno_run 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": {
    "juno_run": {
      "limits": [
        {
          "counter": "juno_run_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 Junobuild, so you can run agents against it safely.

FAQ

Questions about juno_run

What does the juno_run tool do? +

Run a custom JavaScript or TypeScript script in the CLI context. The script has access to the authenticated Juno environment. It is categorised as a Execute tool in the Junobuild MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on juno_run? +

Register the Junobuild MCP server in PolicyLayer and add a rule for juno_run: 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 Junobuild. Nothing to install.

What risk level is juno_run? +

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

Can I rate-limit juno_run? +

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

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

juno_run is provided by the Junobuild MCP server (junobuild-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.