start_saddle_search · Fairchem MCP: Risk & Policy

WHAT IT DOES

What start_saddle_search does on Fairchem

AI agents invoke start_saddle_search 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_saddle_search needs a policy

This tool initiates a saddle point search, which is a complex computational chemistry operation that triggers external simulation code execution. While the tool description is empty, the server context and sibling tools (execute, build_structure, get_trajectory) confirm this is part of a computational chemistry simulation framework where operations execute code with effects dependent on arguments.

From the tool's definition Tool name 'start_saddle_search' and server description indicating it 'allows LLM agents to load a model once and steer relaxations, MD, NEB, phonons, and minima searches mid-flight.' Saddle point searches are computational simulations that execute external…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_saddle_search Rate-limited

start_saddle_search 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_saddle_search": {
      "limits": [
        {
          "counter": "start_saddle_search_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_saddle_search

What does the start_saddle_search tool do? +

start_saddle_search. 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_saddle_search? +

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

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

Can I rate-limit start_saddle_search? +

Yes. Add a rate_limit block to the start_saddle_search 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_saddle_search completely? +

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

start_saddle_search 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.