AI agents call get_trajectory to retrieve information from Fairchem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries simulation results without side effects. It does not create, modify, delete, or execute code. The blast radius if misused is minimal—an agent can only access historical trajectory information, which poses no operational risk to the simulation infrastructure or data integrity.
From the tool's definition Tool returns historical data ('energy/force history') without modifying, deleting, or executing operations. The name and description indicate a retrieval operation ('Return') that observes simulation state ('last_n snapshots').
Attacks that exploit this kind of access
Return the recent energy/force history of a job (last_n snapshots). It is categorised as a Read tool in the Fairchem MCP Server, which means it retrieves data without modifying state.
Register the Fairchem MCP server in PolicyLayer and add a rule for get_trajectory: 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.
get_trajectory is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_trajectory 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 get_trajectory. 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.
get_trajectory 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 →