webgpu_pipeline_dump
Enumerate active render/compute pipelines, bind-group layouts, and render-pass descriptors by hooking GPUDevice createRenderPipeline / createComputePipeline / createBindGroupLayout (plus async variants). Captures the full descriptor (vertex/fragment entry points, buffer stride/attributes, bind-gr...
This record as markdown: /tools/io-github-vmoranv-jshookmcp/webgpu-pipeline-dump.md
What webgpu_pipeline_dump does on Jshookmcp
AI agents call webgpu_pipeline_dump 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_pipeline_dump is rated Low
The tool hooks GPU device methods to observe and enumerate pipeline configurations and descriptor layouts. It retrieves and captures metadata about existing GPU resources without modifying, deleting, or executing code. This is a read-only information gathering capability with minimal security impact—it exposes GPU pipeline structure but cannot alter state or trigger unintended computation.
From the tool's definition Tool performs enumeration and capture of GPU pipeline metadata through hooks: 'Enumerate active render/compute pipelines', 'Captures the full descriptor'. No modification, deletion, or code execution capability—purely observational introspection of GPU state.
Attacks that exploit this kind of access
The rule that runs webgpu_pipeline_dump 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_pipeline_dump, this is the rule to start with:
webgpu_pipeline_dump 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_pipeline_dump call is checked against it from then on.
Questions about webgpu_pipeline_dump
Enumerate active render/compute pipelines, bind-group layouts, and render-pass descriptors by hooking GPUDevice createRenderPipeline / createComputePipeline / createBindGroupLayout (plus async variants). Captures the full descriptor (vertex/fragment entry points, buffer stride/attributes, bind-group layout entries, visibility) so a captured bindGroups index can be resolved to actual resources. 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_pipeline_dump: 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_pipeline_dump 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_pipeline_dump 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_pipeline_dump. 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_pipeline_dump 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