Auto-detect render pass boundaries and summarize each pass. Detects passes by Clear actions and output target changes. Returns a list of render passes with draw count, RT info, and event range.
AI agents call analyze_render_passes 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 is a read-only analysis tool that inspects GPU frame capture data to extract and report information about render pass structure. It retrieves and processes existing capture data without creating, modifying, or destructively altering anything. The blast radius of misuse is minimal—an AI agent cannot cause financial loss, data corruption, or system damage by analyzing render passes incorrectly.
From the tool's definition Tool analyzes and summarizes existing render pass boundaries by detecting Clear actions and output target changes, returning metadata (draw count, RT info, event range). The description uses passive analysis verbs: 'auto-detect', 'summarize', 'returns'.
Documented attack patterns abuse exactly the kind of access analyze_render_passes 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 analyze_render_passes:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_render_passes": {}
}
}analyze_render_passes 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.
Auto-detect render pass boundaries and summarize each pass. Detects passes by Clear actions and output target changes. Returns a list of render passes with draw count, RT info, and event range. 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 analyze_render_passes: 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.
analyze_render_passes 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 analyze_render_passes 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 analyze_render_passes. 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.
analyze_render_passes 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.