stop_model · Tenzro Ledger MCP: Risk & Policy

WHAT IT DOES

What stop_model does on Tenzro Ledger MCP

AI agents invoke stop_model to trigger actions in Tenzro Ledger MCP. 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 stop_model needs a policy

The tool executes a command to stop a model server process. While not immediately destructive (the model data persists), it disrupts service availability and represents a state-changing operation on external infrastructure. This fits Execute rather than Write because it triggers/halts an external process rather than creating/modifying data.

From the tool's definition 'Stop serving a model on this node' - this is an operational action that halts a running service/process. It triggers an external operation (stopping a model server) whose effects depend on which model is being stopped.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_model Rate-limited

stop_model 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": {
    "stop_model": {
      "limits": [
        {
          "counter": "stop_model_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 Tenzro Ledger MCP, so you can run agents against it safely.

FAQ

Questions about stop_model

What does the stop_model tool do? +

Stop serving a model on this node. It is categorised as a Execute tool in the Tenzro Ledger MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_model? +

Register the Tenzro Ledger MCP server in PolicyLayer and add a rule for stop_model: 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 Tenzro Ledger MCP. Nothing to install.

What risk level is stop_model? +

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

Can I rate-limit stop_model? +

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

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

stop_model is provided by the Tenzro Ledger MCP server (https://canton-mcp.tenzro.network/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.