AI agents use export_mesh_stage_data to create or update resources in Renderdoc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Renderdoc environment.
This tool creates or extracts data from a GPU frame capture and writes it to an output format, which constitutes a Write operation. The severity is low because: (1) it operates on already-captured debug data, not live system resources; (2) the effect is read-only in terms of the original capture file; (3) exported mesh data is forensic/analytical output with no side effects on the debugged application or system.
From the tool's definition export_mesh_stage_data performs an export operation that writes mesh stage data to output format (vsin/vsout stages are vertex shader input/output). The description states '导出一个 mesh stage' (export a mesh stage).
Attacks that exploit this kind of access
导出一个 mesh stage。常用 stage 是 vsin 和 vsout。. It is categorised as a Write tool in the Renderdoc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Renderdoc MCP server in PolicyLayer and add a rule for export_mesh_stage_data: 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 Renderdoc. Nothing to install.
export_mesh_stage_data 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 export_mesh_stage_data 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 export_mesh_stage_data. 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.
export_mesh_stage_data is provided by the Renderdoc MCP server (kenzo1024/renderdocmcp). 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 →