Undo a patch_bytes/nop by its id (writes the original bytes back).
AI agents use restore_patch to create or update resources in GTAV-CLAUDE-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GTAV-CLAUDE-MCP environment.
This tool modifies game memory by restoring original bytes, making it a Write operation rather than a pure Read. While the restoration itself is technically reversible (the inverse of a prior patch), the act of writing to memory has side effects on game state.
From the tool's definition Tool description states it 'writes the original bytes back', which is a memory write operation that modifies game state. The tool reverses a previous patch but still constitutes a write action.
Attacks that exploit this kind of access
Undo a patch_bytes/nop by its id (writes the original bytes back). It is categorised as a Write tool in the GTAV-CLAUDE-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GTAV-CLAUDE- MCP server in PolicyLayer and add a rule for restore_patch: 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.
restore_patch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the restore_patch 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 restore_patch. 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.
restore_patch 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 →