load_model · Fairchem MCP: Risk & Policy

WHAT IT DOES

What load_model does on Fairchem

AI agents invoke load_model to trigger actions in Fairchem. 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 load_model needs a policy

Loading a model into memory is not a simple read operation — it triggers external computation (model initialization, memory allocation, potentially GPU resource acquisition) and establishes a persistent resident process/object in memory. This constitutes executing an external operation whose effects depend on the model argument chosen. It is not destructive or financial, but it does more than passively retrieve data.

From the tool's definition Load a FAIRChem model as an ASE calculator, kept resident in memory

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_model Rate-limited

load_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": {
    "load_model": {
      "limits": [
        {
          "counter": "load_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 Fairchem, so you can run agents against it safely.

FAQ

Questions about load_model

What does the load_model tool do? +

Load a FAIRChem model as an ASE calculator, kept resident in memory. It is categorised as a Execute tool in the Fairchem MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on load_model? +

Register the Fairchem MCP server in PolicyLayer and add a rule for load_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 Fairchem. Nothing to install.

What risk level is load_model? +

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

Can I rate-limit load_model? +

Yes. Add a rate_limit block to the load_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 load_model completely? +

Set action: deny in the PolicyLayer policy for load_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 load_model? +

load_model is provided by the Fairchem MCP server (jkitchin/fairchem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.