AI agents call vehicle.recalls 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 is a lookup/search tool that queries publicly available NHTSA recall information and returns results. It has no side effects, does not modify data, execute code, delete records, or handle financial transactions. The pay-per-call settlement mechanism on the MCP server is a billing artifact, not a function of this specific tool.
From the tool's definition Tool description states it 'Search[es] by VIN...or make/model/year, or NHTSA campaign ID. Returns recall ID, component, summary, consequence, remedy, dates.' — purely retrieves and returns data from NHTSA vehicle recall database with no modification,…
Attacks that exploit this kind of access
NHTSA vehicle recall lookup. Search by VIN (precise), or make/model/year, or NHTSA campaign ID. Returns recall ID, component, summary, consequence, remedy, dates. 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.recalls: 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.recalls 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.recalls 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.recalls. 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.recalls 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 →