webgpu_shader_source_capture
Capture WGSL shader sources a running app compiles via GPUDevice.createShaderModule — the only artifact revealing what a compute/render pipeline computes (e.g. physics vs. cryptominer). Pairs with webgpu_capture_commands to reconstruct what data each draw/dispatch operated on.
This record as markdown: /tools/io-github-vmoranv-jshookmcp/webgpu-shader-source-capture.md
What webgpu_shader_source_capture does on Jshookmcp
AI agents call webgpu_shader_source_capture to retrieve information from Jshookmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why webgpu_shader_source_capture is rated Low
The tool observes and extracts compiled shader source code from a running JavaScript/WebGPU application. This is fundamentally a Read operation—it retrieves artifacts (shader code and inferred data flow) for analysis purposes.
From the tool's definition Tool captures WGSL shader sources compiled by a running app via GPUDevice.createShaderModule. The description states it reveals 'what a compute/render pipeline computes' and pairs with command capture to 'reconstruct what data each draw/dispatch operated on.'…
Attacks that exploit this kind of access
The rule that runs webgpu_shader_source_capture safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Jshookmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For webgpu_shader_source_capture, this is the rule to start with:
webgpu_shader_source_capture is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Jshookmcp, apply this rule, and every webgpu_shader_source_capture call is checked against it from then on.
Questions about webgpu_shader_source_capture
Capture WGSL shader sources a running app compiles via GPUDevice.createShaderModule — the only artifact revealing what a compute/render pipeline computes (e.g. physics vs. cryptominer). Pairs with webgpu_capture_commands to reconstruct what data each draw/dispatch operated on. It is categorised as a Read tool in the Jshookmcp MCP Server, which means it retrieves data without modifying state.
Register the Jshook MCP server in PolicyLayer and add a rule for webgpu_shader_source_capture: 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 Jshookmcp. Nothing to install.
webgpu_shader_source_capture 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 webgpu_shader_source_capture 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 webgpu_shader_source_capture. 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.
webgpu_shader_source_capture is provided by the Jshook MCP server (@jshookmcp/jshook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Jshook, and thousands of servers like it.
This server
Across the catalogue