Find code references (RIP-relative LEA + rel32 CALL/JMP) to an address. Walk string->func->callers.
AI agents call find_xrefs 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 performs static analysis by searching for and walking code references (cross-references) in a binary or memory space. It retrieves information about where code addresses are referenced but does not execute code, modify memory, delete data, or perform financial operations. The action is purely informational—tracing caller relationships in existing code.
From the tool's definition Tool name 'find_xrefs' and description 'Find code references' and 'Walk string->func->callers' indicate retrieval and analysis of existing code references without modification or execution.
Attacks that exploit this kind of access
Find code references (RIP-relative LEA + rel32 CALL/JMP) to an address. Walk string->func->callers. 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 find_xrefs: 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.
find_xrefs 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 find_xrefs 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 find_xrefs. 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.
find_xrefs 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 →