govern · Sovereign Stack MCP: Risk & Policy

WHAT IT DOES

What govern does on Sovereign Stack

AI agents invoke govern to trigger actions in Sovereign Stack. 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 govern needs a policy

govern 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

govern Rate-limited

govern 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": {
    "govern": {
      "limits": [
        {
          "counter": "govern_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 Sovereign Stack, so you can run agents against it safely.

FAQ

Questions about govern

What does the govern tool do? +

Run full governance circuit: detect → simulate → deliberate. It is categorised as a Execute tool in the Sovereign Stack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on govern? +

Register the Sovereign Stack MCP server in PolicyLayer and add a rule for govern: 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 Sovereign Stack. Nothing to install.

What risk level is govern? +

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

Can I rate-limit govern? +

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

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

govern is provided by the Sovereign Stack MCP server (templetwo/sovereign-stack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.