AI agents invoke start_minima_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.
The tool initiates a minima search simulation, which is a code/computational execution that runs algorithms whose effects depend on the input structure and parameters. This is not a simple data read (it produces side effects via simulation), not reversible like a write, and not destructive in the sense of deletion. However, it commits significant computational resources and may alter internal state mid-flight.
From the tool's definition Tool name 'start_minima_search' combined with server context describing 'steer relaxations, MD, NEB, phonons, and minima searches mid-flight' indicates this tool triggers a computationally expensive simulation/optimization operation.
Attacks that exploit this kind of access
start_minima_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.
Register the Fairchem MCP server in PolicyLayer and add a rule for start_minima_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.
start_minima_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_minima_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.
Set action: deny in the PolicyLayer policy for start_minima_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.
start_minima_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →