AI agents call get_pass_timing to retrieve information from Renderdoc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or query timing information from RenderDoc GPU captures without modifying or executing operations. It fits the Read category as it retrieves performance timing data for analysis. The severity is low because timing data queries have no side effects on the system or graphics state.
From the tool's definition Tool name 'get_pass_timing' and server context indicate retrieval of timing data from GPU frame captures. The sibling tools (analyze_bandwidth, analyze_overdraw, analyze_render_passes) and server description emphasize 'analyzing', 'inspecting', and…
Documented attack patterns abuse exactly the kind of access get_pass_timing gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Renderdoc, and nothing reaches the server without passing your rules. This is the rule we recommend for get_pass_timing:
{
"version": "1",
"default": "deny",
"tools": {
"get_pass_timing": {}
}
}get_pass_timing is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_pass_timing. It is categorised as a Read tool in the Renderdoc MCP Server, which means it retrieves data without modifying state.
Register the Renderdoc MCP server in PolicyLayer and add a rule for get_pass_timing: 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.
get_pass_timing 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 get_pass_timing 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 get_pass_timing. 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.
get_pass_timing is provided by the Renderdoc MCP server (linkingooo/renderdoc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Renderdoc, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Renderdoc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.