Probe vehicle memory to find wheel array offset.
AI agents call probe_wheels to retrieve information from GTAV-CLAUDE-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The probe_wheels tool reads game memory to locate data structures (wheel array offsets in vehicles). This is a lookup/query operation with no side effects, permanent changes, or code execution. While it accesses memory, the action itself is observational rather than destructive, executable, or write-capable.
From the tool's definition Tool performs memory probing to 'find wheel array offset' — a read-only information gathering operation that queries game memory structures without modifying or executing arbitrary code.
Attacks that exploit this kind of access
Probe vehicle memory to find wheel array offset. It is categorised as a Read tool in the GTAV-CLAUDE-MCP MCP Server, which means it retrieves data without modifying state.
Register the GTAV-CLAUDE- MCP server in PolicyLayer and add a rule for probe_wheels: 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 GTAV-CLAUDE-MCP. Nothing to install.
probe_wheels 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 probe_wheels 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 probe_wheels. 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.
probe_wheels is provided by the GTAV-CLAUDE- MCP server (tabbedscamper/gtav-claude-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 →