AI agents invoke start_convex_hull 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.
Convex hull calculations in materials science typically involve triggering external simulation operations whose effects depend on input structures and parameters. While the empty description reduces confidence, the context (FAIRChem simulations, ASE workflows, sibling execute/MD tools) strongly suggests this initiates a computational process rather than merely reading data.
From the tool's definition Tool name 'start_convex_hull' in context of FAIRChem/ASE simulation server; sibling tools include 'execute', 'start_neb', 'start_md' indicating this triggers computational workflows. Description is empty, limiting specificity.
Attacks that exploit this kind of access
start_convex_hull. 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_convex_hull: 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_convex_hull 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_convex_hull 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_convex_hull. 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_convex_hull 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 →