AI agents use close_capture 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.
Closing a capture is a reversible write operation—it transitions the capture state from open to closed without deleting underlying data or files. The user can reopen the same capture file later. This is distinct from destructive operations (which would delete files) or execute operations (which would run code). The blast radius is minimal since it only affects the current session state with no external side effects.
From the tool's definition Tool description states '关闭当前 capture' (Close the current capture). This is a state modification operation that closes/unloads an open capture session.
Attacks that exploit this kind of access
关闭当前 capture。. 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 close_capture: 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.
close_capture 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 close_capture 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 close_capture. 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.
close_capture 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 →