runOnce · Sugar MCP: Risk & Policy

WHAT IT DOES

What runOnce does on Sugar

AI agents invoke runOnce to trigger actions in Sugar. 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 runOnce needs a policy

runOnce 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

runOnce Rate-limited

runOnce 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": {
    "runOnce": {
      "limits": [
        {
          "counter": "runonce_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 Sugar, so you can run agents against it safely.

FAQ

Questions about runOnce

What does the runOnce tool do? +

Execute one autonomous development cycle (picks up highest priority task). It is categorised as a Execute tool in the Sugar MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on runOnce? +

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

What risk level is runOnce? +

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

Can I rate-limit runOnce? +

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

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

runOnce is provided by the Sugar MCP server (pypi:sugarai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.