add_model · Llauncher MCP: Risk & Policy

WHAT IT DOES

What add_model does on Llauncher

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

WHY IT NEEDS A POLICY

Why add_model needs a policy

This tool creates or registers a new model configuration, which is a reversible write operation. It does not execute code or delete data, nor does it involve financial transactions. The severity is medium because misconfiguration could impact inference server availability or resource consumption, but the action itself is reversible—configurations can be updated or removed.

From the tool's definition Tool name 'add_model' and description 'Add a new model configuration' indicate creation of new data. The server manages llama.cpp instances, and adding a model configuration creates a new reversible entry in the system's model registry.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_model Rate-limited

add_model 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": {
    "add_model": {
      "limits": [
        {
          "counter": "add_model_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 Llauncher, so you can run agents against it safely.

FAQ

Questions about add_model

What does the add_model tool do? +

Add a new model configuration. It is categorised as a Write tool in the Llauncher MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_model? +

Register the Llauncher MCP server in PolicyLayer and add a rule for add_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 Llauncher. Nothing to install.

What risk level is add_model? +

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

Can I rate-limit add_model? +

Yes. Add a rate_limit block to the add_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 add_model completely? +

Set action: deny in the PolicyLayer policy for add_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 add_model? +

add_model is provided by the Llauncher MCP server (shanevcantwell/llauncher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.