fm_generate · Pypi:apple Fm MCP: Risk & Policy

WHAT IT DOES

What fm_generate does on Pypi:apple Fm

AI agents invoke fm_generate to trigger actions in Pypi:apple Fm. 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 fm_generate needs a policy

This tool executes an on-device language model to generate text. It is not a simple read/query operation; it actively runs inference on Apple's Neural Engine, whose output depends on the arguments provided. The description is truncated and uninformative beyond the basic premise, so confidence is moderate.

From the tool's definition 'Generate text using Apple' — triggers an on-device LLM (3B parameter model) to produce text output based on input arguments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fm_generate Rate-limited

fm_generate 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": {
    "fm_generate": {
      "limits": [
        {
          "counter": "fm_generate_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 Pypi:apple Fm, so you can run agents against it safely.

FAQ

Questions about fm_generate

What does the fm_generate tool do? +

Generate text using Apple. It is categorised as a Execute tool in the Pypi:apple Fm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fm_generate? +

Register the Pypi:apple Fm MCP server in PolicyLayer and add a rule for fm_generate: 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 Pypi:apple Fm. Nothing to install.

What risk level is fm_generate? +

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

Can I rate-limit fm_generate? +

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

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

fm_generate is provided by the Pypi:apple Fm MCP server (pypi:apple-fm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.