Get reflection information for the shader at the specified stage. Returns input/output signatures, constant buffer layouts, and resource bindings. Args: stage: Shader stage (vertex, hull, domain, geometry, pixel, compute). event_id: Optional event ID to navigate to first.
AI agents call get_shader_reflection 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 retrieves and queries metadata about shader structure (reflection information) from an already-loaded GPU frame capture. It performs introspection only—reading shader stage details, signatures, and bindings without modifying the capture, executing code, or triggering external operations. This is a pure Read operation typical of debugging/analysis workflows.
From the tool's definition Tool description states it 'Get reflection information' and 'Returns input/output signatures, constant buffer layouts, and resource bindings.' The verb 'Get' and 'Returns' indicate data retrieval with no modification. No side effects are mentioned.
Documented attack patterns abuse exactly the kind of access get_shader_reflection 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_shader_reflection:
{
"version": "1",
"default": "deny",
"tools": {
"get_shader_reflection": {}
}
}get_shader_reflection 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 reflection information for the shader at the specified stage. Returns input/output signatures, constant buffer layouts, and resource bindings. Args: stage: Shader stage (vertex, hull, domain, geometry, pixel, compute). event_id: Optional event ID to navigate to first. 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_shader_reflection: 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_shader_reflection 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_shader_reflection 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_shader_reflection. 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_shader_reflection 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.