complete_experiment · Sovereign Stack MCP: Risk & Policy

WHAT IT DOES

What complete_experiment does on Sovereign Stack

AI agents use complete_experiment to create or update resources in Sovereign Stack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sovereign Stack environment.

WHY IT NEEDS A POLICY

Why complete_experiment needs a policy

An AI agent can call complete_experiment faster than any human can review — one bad instruction and it creates or modifies resources in Sovereign Stack by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_experiment Rate-limited

complete_experiment stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "complete_experiment": {
      "limits": [
        {
          "counter": "complete_experiment_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 complete_experiment

What does the complete_experiment tool do? +

Record results of a completed experiment. It is categorised as a Write tool in the Sovereign Stack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on complete_experiment? +

Register the Sovereign Stack MCP server in PolicyLayer and add a rule for complete_experiment: 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 complete_experiment? +

complete_experiment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit complete_experiment? +

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

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

complete_experiment 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.