Low Risk

get_pipeline_state

Get the full graphics pipeline state at the current or specified event. Returns topology, viewports, scissors, rasterizer, blend, depth, stencil state, bound shaders, and output targets. Args: event_id: Optional event ID to navigate to first. Uses current event if omitted.

How to control get_pipeline_state ↓

What get_pipeline_state does on Renderdoc

AI agents call get_pipeline_state 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.

Low Risk

Why get_pipeline_state needs a policy

This tool purely queries and retrieves information about the current GPU graphics pipeline state at a specified event. It performs introspection and analysis of existing frame capture data without creating, modifying, deleting, or executing operations. The optional event_id parameter allows navigation but does not alter state.

From the tool's definition Tool description states it 'Get[s] the full graphics pipeline state' and 'Returns topology, viewports, scissors, rasterizer, blend, depth, stencil state, bound shaders, and output targets.' The verb 'Get' and 'Returns' indicate data retrieval with no…

Documented attack patterns abuse exactly the kind of access get_pipeline_state gives an agent:

How to control get_pipeline_state

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_pipeline_state:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_pipeline_state": {}
  }
}

get_pipeline_state is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Renderdoc — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about get_pipeline_state

What does the get_pipeline_state tool do? +

Get the full graphics pipeline state at the current or specified event. Returns topology, viewports, scissors, rasterizer, blend, depth, stencil state, bound shaders, and output targets. Args: event_id: Optional event ID to navigate to first. Uses current event if omitted. It is categorised as a Read tool in the Renderdoc MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_pipeline_state? +

Register the Renderdoc MCP server in PolicyLayer and add a rule for get_pipeline_state: 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.

What risk level is get_pipeline_state? +

get_pipeline_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_pipeline_state? +

Yes. Add a rate_limit block to the get_pipeline_state 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.

How do I block get_pipeline_state completely? +

Set action: deny in the PolicyLayer policy for get_pipeline_state. 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.

What MCP server provides get_pipeline_state? +

get_pipeline_state 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.

Enforce policy on every Renderdoc tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.