AI agents use export_draw_bundle 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.
The tool writes data (vertex shader inputs/outputs, textures, and manifest metadata) to files or exports them from the RenderDoc capture. This is a reversible write operation that creates output artifacts without permanently modifying the underlying capture file or executing arbitrary code.
From the tool's definition Tool name 'export_draw_bundle' combined with description stating it exports 'VSIn, VSOut, textures and manifest' indicates the tool creates/writes output files containing graphics pipeline data extracted from GPU frame captures.
Attacks that exploit this kind of access
导出 VSIn、VSOut、纹理和 manifest。. 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_draw_bundle: 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_draw_bundle 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_draw_bundle 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_draw_bundle. 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_draw_bundle 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 →