AI agents call vehicle.decode-wmi 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 pure data retrieval tool that maps a VIN prefix to manufacturer information. It performs no destructive actions, executes no code, modifies no data, and involves no financial transactions. The operation is read-only and has no blast radius if misused by an AI agent.
From the tool's definition Tool decodes a 3-character World Manufacturer Identifier from a VIN to identify the manufacturer—a straightforward lookup operation with no side effects, data modification, or external state changes.
Attacks that exploit this kind of access
Decode a 3-character World Manufacturer Identifier (WMI), the first 3 chars of a VIN, to manufacturer. 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.decode-wmi: 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.decode-wmi 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.decode-wmi 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.decode-wmi. 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.decode-wmi 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 →