debug_shader_at_pixel
AI agents call debug_shader_at_pixel 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.
The tool appears designed to inspect and debug shader execution at a specific pixel location within a GPU frame capture. This is a read-only diagnostic operation that retrieves information about shader state and behavior without modifying the capture or executing arbitrary code. It falls into the Read category as it queries/inspects existing frame capture data.
From the tool's definition Tool name 'debug_shader_at_pixel' combined with server context indicating 'graphics debugging and performance analysis' and sibling tools like 'analyze_bandwidth', 'analyze_overdraw', 'analyze_render_passes' which are all analysis/inspection operations.
Documented attack patterns abuse exactly the kind of access debug_shader_at_pixel 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 debug_shader_at_pixel:
{
"version": "1",
"default": "deny",
"tools": {
"debug_shader_at_pixel": {}
}
} debug_shader_at_pixel 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.
debug_shader_at_pixel. 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 debug_shader_at_pixel: 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.
debug_shader_at_pixel 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 debug_shader_at_pixel 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 debug_shader_at_pixel. 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.
debug_shader_at_pixel 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.