Low Risk

get_capture_info

Get information about the currently open capture. Returns API type, file path, action count, texture/buffer counts, and known GPU quirks based on the detected driver/GPU.

How to control get_capture_info ↓

What get_capture_info does on Renderdoc

AI agents call get_capture_info 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_capture_info needs a policy

This tool retrieves and queries existing capture metadata without side effects. It does not execute code, modify data, delete resources, or trigger external operations. The returned information (API type, counts, driver quirks) is read-only diagnostics. Severity is low because misuse would only expose debugging information about a graphics frame capture, not compromise systems or delete data.

From the tool's definition Tool name 'get_capture_info' and description 'Get information about the currently open capture' indicates retrieval of metadata about an open frame capture.

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

How to control get_capture_info

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_capture_info:

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

get_capture_info 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_capture_info

What does the get_capture_info tool do? +

Get information about the currently open capture. Returns API type, file path, action count, texture/buffer counts, and known GPU quirks based on the detected driver/GPU. 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_capture_info? +

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

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

Can I rate-limit get_capture_info? +

Yes. Add a rate_limit block to the get_capture_info 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_capture_info completely? +

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

get_capture_info 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.