AI agents call vehicle.manufacturers 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 queries public vehicle manufacturer registry data and returns results. It is a straightforward read operation that retrieves existing information without creating, modifying, deleting, or executing any operations. The low severity reflects that misuse would only expose publicly available regulatory data with no blast radius for the data source or user accounts.
From the tool's definition Tool returns a 'Paginated list' of vehicle manufacturers from NHTSA vPIC database—a pure data retrieval operation with no side effects, modification, or external state changes.
Attacks that exploit this kind of access
Paginated list of all NHTSA-registered vehicle manufacturers (vPIC). 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.manufacturers: 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.manufacturers 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.manufacturers 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.manufacturers. 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.manufacturers 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 →