Read a script-VM Global_<index> (gameplay/mission state) via ScriptHookV. kind: int|uint|float|hex.
AI agents call read_global 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 queries internal game state variables (gameplay/mission state globals) without modifying them. Reading game memory for inspection purposes has minimal security impact in the context of an AI agent — it gathers information but produces no side effects or state changes. The low severity reflects that read-only access to game state cannot cause damage.
From the tool's definition Tool name is 'read_global' and description states 'Read a script-VM Global_<index>' — the verb 'read' and absence of any modification capability clearly indicate data retrieval only.
Attacks that exploit this kind of access
Read a script-VM Global_<index> (gameplay/mission state) via ScriptHookV. kind: int|uint|float|hex. 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 read_global: 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.
read_global 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 read_global 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 read_global. 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.
read_global 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 →