AI agents invoke start_sella_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.
This tool triggers execution of a computational simulation (saddle-point/minima search) whose effects depend on the structure and parameters provided. While not directly destructive, it runs external operations that consume compute resources and modify simulation state.
From the tool's definition Tool name 'start_sella_search' combined with server description stating it 'allows LLM agents to...steer...minima searches mid-flight' and sibling tools include 'execute', 'get_status', 'get_trajectory' indicating computational workflow control.
Attacks that exploit this kind of access
start_sella_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_sella_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_sella_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_sella_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_sella_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_sella_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 →