Check your vehicle
AI agents call rivian_get_vehicle_state to retrieve information from Rivian MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves vehicle state information (battery level, charging status, OTA update status) without modifying any data or triggering external actions. It is purely observational/monitoring functionality. The explicit 'read-only access' statement in the server description confirms no write or execute capabilities.
From the tool's definition Tool name 'rivian_get_vehicle_state' and description 'Check your vehicle' combined with server description stating 'read-only access to vehicle data' and ability to 'monitor battery levels, OTA updates, and charging status' indicates data retrieval with no…
Attacks that exploit this kind of access
Check your vehicle. It is categorised as a Read tool in the Rivian MCP MCP Server, which means it retrieves data without modifying state.
Register the Rivian MCP server in PolicyLayer and add a rule for rivian_get_vehicle_state: 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 Rivian MCP. Nothing to install.
rivian_get_vehicle_state 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 rivian_get_vehicle_state 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 rivian_get_vehicle_state. 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.
rivian_get_vehicle_state is provided by the Rivian MCP server (patrickheneise/rivian-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 →