Disassemble the shader bound at the specified stage. If target is omitted, tries all available targets in order and returns the first successful result. Falls back to reflection info if all disassembly fails. Args: stage: Shader stage (vertex, hull, domain, geometry, pixel, compute). target: Disa...
AI agents call disassemble_shader 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 analyzes shader disassembly for debugging purposes. It performs inspection and querying of graphics pipeline state with no side effects—no data is created, modified, deleted, or persisted. Even though it operates on GPU captures, the actions are purely analytical reads.
From the tool's definition Tool name 'disassemble_shader' and description explicitly states it disassembles and returns shader information.
Documented attack patterns abuse exactly the kind of access disassemble_shader 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 disassemble_shader:
{
"version": "1",
"default": "deny",
"tools": {
"disassemble_shader": {}
}
}disassemble_shader 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.
Disassemble the shader bound at the specified stage. If target is omitted, tries all available targets in order and returns the first successful result. Falls back to reflection info if all disassembly fails. Args: stage: Shader stage (vertex, hull, domain, geometry, pixel, compute). target: Disassembly target/format. If omitted, tries all available targets. event_id: Optional event ID to navigate to first. line_range: [start_line, end_line] (1-based). Only return lines in this range. search: Keyword to search in the disassembly. Returns matching lines with 5 lines of context before and after each match. 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 disassemble_shader: 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.
disassemble_shader 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 disassemble_shader 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 disassemble_shader. 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.
disassemble_shader 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.