AI agents call lookup_recalls to retrieve information from VIN MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available safety recall information from NHTSA based on a VIN input. It performs a lookup/query operation with no side effects, no data modification, and no execution of commands. The worst outcome of misuse would be retrieving recall information for an unintended vehicle, which is a minor privacy/information leakage concern but not a significant security risk.
From the tool's definition Tool description states it 'Look up NHTSA safety recalls for a vehicle by VIN' and 'Returns recall campaigns, affected components, consequences, and remedies' — purely informational retrieval with no modifications, deletions, or external operations triggered.
Attacks that exploit this kind of access
Look up NHTSA safety recalls for a vehicle by VIN. Returns recall campaigns, affected components, consequences, and remedies. It is categorised as a Read tool in the VIN MCP MCP Server, which means it retrieves data without modifying state.
Register the VIN MCP server in PolicyLayer and add a rule for lookup_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 VIN MCP. Nothing to install.
lookup_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 lookup_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 lookup_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.
lookup_recalls is provided by the VIN MCP server (keptlive/vin-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 →