Search draw calls by rendering state filters. Iterates through draw calls checking pipeline state. This can be slow for large captures as it must set_event for each draw call. Args: blend: Filter by blend enabled state (True/False). min_vertices: Minimum vertex count to include. texture_id: Only ...
AI agents call find_draws 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 performs a search and inspection operation over existing GPU frame capture data. It filters and queries draw calls based on rendering state without modifying the capture, executing code, or causing side effects. The iteration through draw calls and pipeline state inspection are read-only analysis operations typical of debugging tools.
From the tool's definition Tool name is 'find_draws' and description states it 'Search[es] draw calls by rendering state filters' and 'Iterates through draw calls checking pipeline state.' All parameters are filter/query inputs (blend state, vertex count thresholds, resource IDs,…
Documented attack patterns abuse exactly the kind of access find_draws 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 find_draws:
{
"version": "1",
"default": "deny",
"tools": {
"find_draws": {}
}
}find_draws 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.
Search draw calls by rendering state filters. Iterates through draw calls checking pipeline state. This can be slow for large captures as it must set_event for each draw call. Args: blend: Filter by blend enabled state (True/False). min_vertices: Minimum vertex count to include. texture_id: Only draws using this texture resource ID. shader_id: Only draws using this shader resource ID. render_target_id: Only draws targeting this render target. max_results: Maximum results to return (default 50). 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 find_draws: 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.
find_draws 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 find_draws 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 find_draws. 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.
find_draws 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.