Low Risk

read_texture_pixels

Read actual pixel values from a rectangular region of a texture. Returns float RGBA values for each pixel. Region is capped at 64x64. Useful for precisely checking IBL cubemap faces, LUT textures, history buffers, etc. Args: resource_id: The texture resource ID string. x: Top-left X coordinate of...

How to control read_texture_pixels ↓

What read_texture_pixels does on Renderdoc

AI agents call read_texture_pixels 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 read_texture_pixels needs a policy

This tool exclusively reads and retrieves pixel data from GPU textures without any capability to modify, delete, or execute code. It has no side effects beyond data retrieval. The 64x64 region cap and read-only nature confirm this is a simple data query operation.

From the tool's definition Tool name is 'read_texture_pixels' and description states 'Read actual pixel values from a rectangular region of a texture. Returns float RGBA values for each pixel.' The operation is purely retrieving texture data with no modification capability.

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

How to control read_texture_pixels

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 read_texture_pixels:

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

read_texture_pixels 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 read_texture_pixels

What does the read_texture_pixels tool do? +

Read actual pixel values from a rectangular region of a texture. Returns float RGBA values for each pixel. Region is capped at 64x64. Useful for precisely checking IBL cubemap faces, LUT textures, history buffers, etc. Args: resource_id: The texture resource ID string. x: Top-left X coordinate of the region. y: Top-left Y coordinate of the region. width: Region width (max 64). height: Region height (max 64). mip_level: Mip level to read (default 0). array_slice: Array slice or cubemap face index (default 0). Cubemap face order: 0=+X 1=-X 2=+Y 3=-Y 4=+Z 5=-Z. 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.

How do I enforce a policy on read_texture_pixels? +

Register the Renderdoc MCP server in PolicyLayer and add a rule for read_texture_pixels: 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 read_texture_pixels? +

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

Can I rate-limit read_texture_pixels? +

Yes. Add a rate_limit block to the read_texture_pixels 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 read_texture_pixels completely? +

Set action: deny in the PolicyLayer policy for read_texture_pixels. 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 read_texture_pixels? +

read_texture_pixels 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.