NHTSA NCAP 5-Star crash-test ratings by make/model/year. Returns one item per crash-tested body style with overall/front/side/rollover star ratings, rollover probability, crash-avoidance tech flags, and complaint/recall/investigation counts. Untested vehicles return an empty list.
AI agents call vehicle.safety-ratings to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool has no side effects and performs a straightforward data lookup of publicly available vehicle safety information. No data is created, modified, deleted, or executed. The tool is purely informational and read-only, fitting the 'Read' category as it 'retrieves or queries data; no side effects'.
From the tool's definition Tool retrieves and queries NHTSA crash-test ratings data by vehicle make/model/year. Returns ratings, statistics, and counts with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
NHTSA NCAP 5-Star crash-test ratings by make/model/year. Returns one item per crash-tested body style with overall/front/side/rollover star ratings, rollover probability, crash-avoidance tech flags, and complaint/recall/investigation counts. Untested vehicles return an empty list. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for vehicle.safety-ratings: 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 Mcp. Nothing to install.
vehicle.safety-ratings 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 vehicle.safety-ratings 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 vehicle.safety-ratings. 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.
vehicle.safety-ratings is provided by the MCP server (@2sio/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 →