start_eos_scan · Fairchem MCP: Risk & Policy

WHAT IT DOES

What start_eos_scan does on Fairchem

AI agents invoke start_eos_scan 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 start_eos_scan needs a policy

This tool triggers execution of a complex computational workflow (equation-of-state scanning) that runs external simulation code. While not destructive or financial, it performs compute-intensive operations that modify system state during simulation. Severity is high due to potential resource consumption and long-running compute jobs that could be abused or misused by an agent.

From the tool's definition Tool name 'start_eos_scan' indicates initiation of an equation-of-state scan simulation. Server context describes steering of ASE simulations (MD, NEB, phonons, minima searches, relaxations) mid-flight.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_eos_scan Rate-limited

start_eos_scan 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": {
    "start_eos_scan": {
      "limits": [
        {
          "counter": "start_eos_scan_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 start_eos_scan

What does the start_eos_scan tool do? +

start_eos_scan. 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 start_eos_scan? +

Register the Fairchem MCP server in PolicyLayer and add a rule for start_eos_scan: 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 start_eos_scan? +

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

Can I rate-limit start_eos_scan? +

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

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

start_eos_scan 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.