serve_model · Tenzro Ledger MCP: Risk & Policy

WHAT IT DOES

What serve_model does on Tenzro Ledger MCP

AI agents invoke serve_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 serve_model needs a policy

This tool executes inference operations whose effects depend on which model is specified and what queries are run against it. While not immediately destructive or financial, it represents code execution that could consume computational resources, potentially be exploited to access sensitive model outputs, or be used for unauthorized processing.

From the tool's definition Tool name 'serve_model' with description 'Start serving a model for inference on this node' indicates execution of model inference operations on the node, which triggers external computational processes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

serve_model Rate-limited

serve_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": {
    "serve_model": {
      "limits": [
        {
          "counter": "serve_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 serve_model

What does the serve_model tool do? +

Start serving a model for inference 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 serve_model? +

Register the Tenzro Ledger MCP server in PolicyLayer and add a rule for serve_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 serve_model? +

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

Can I rate-limit serve_model? +

Yes. Add a rate_limit block to the serve_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 serve_model completely? +

Set action: deny in the PolicyLayer policy for serve_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 serve_model? +

serve_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.