Low Risk

get_frame_overview

Get a frame-level statistics overview of the current capture. Returns action counts by type, texture/buffer memory totals, main render targets with draw counts, and estimated resolution.

How to control get_frame_overview ↓

What get_frame_overview does on Renderdoc

AI agents call get_frame_overview 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_frame_overview needs a policy

This tool retrieves and queries statistical metadata about a GPU frame capture without performing any side effects, modifications, or executing arbitrary code. It is purely an informational tool for graphics debugging analysis. The data returned (counts, totals, resolution estimates) are read-only observations of already-captured frame data. No resources are created, modified, deleted, or executed.

From the tool's definition Tool 'get_frame_overview' returns frame-level statistics overview including action counts, memory totals, and render target information.

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

How to control get_frame_overview

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_frame_overview:

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

get_frame_overview 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_frame_overview

What does the get_frame_overview tool do? +

Get a frame-level statistics overview of the current capture. Returns action counts by type, texture/buffer memory totals, main render targets with draw counts, and estimated resolution. 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_frame_overview? +

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

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

Can I rate-limit get_frame_overview? +

Yes. Add a rate_limit block to the get_frame_overview 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_frame_overview completely? +

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

get_frame_overview 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.