juno_changes_apply · Junobuild MCP: Risk & Policy

WHAT IT DOES

What juno_changes_apply does on Junobuild

AI agents invoke juno_changes_apply 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_changes_apply needs a policy

This tool applies a submitted change, which triggers an external operation that modifies system state. It is not a simple write (create/update) but an execution of a previously staged change that could affect satellites, hosting, functions, or other managed resources.

From the tool's definition Apply a submitted change by its ID. Optionally create a snapshot before applying and verify the change hash for integrity.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

juno_changes_apply Rate-limited

juno_changes_apply 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_changes_apply": {
      "limits": [
        {
          "counter": "juno_changes_apply_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_changes_apply

What does the juno_changes_apply tool do? +

Apply a submitted change by its ID. Optionally create a snapshot before applying and verify the change hash for integrity. 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_changes_apply? +

Register the Junobuild MCP server in PolicyLayer and add a rule for juno_changes_apply: 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_changes_apply? +

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

Can I rate-limit juno_changes_apply? +

Yes. Add a rate_limit block to the juno_changes_apply 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_changes_apply completely? +

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

juno_changes_apply 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.