Show the current narrowed scan survivors (address + value).
AI agents call scan_results 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.
This tool retrieves and displays scan results without modifying data, executing code, or causing side effects. It is a query/display operation that falls squarely in the Read category. While the server has access to memory and native functions (which could be risky), this specific tool only shows results.
From the tool's definition Tool name 'scan_results' and description 'Show the current narrowed scan survivors (address + value)' indicate a read-only operation that retrieves and displays results from a memory scanning operation.
Attacks that exploit this kind of access
Show the current narrowed scan survivors (address + value). 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 scan_results: 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.
scan_results 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 scan_results 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 scan_results. 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.
scan_results 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 →