Low Risk

diff_draw_calls

Compare two draw calls and return their state differences. Useful for understanding what changed between two similar draw calls. Args: eid1: Event ID of the first draw call. eid2: Event ID of the second draw call.

How to control diff_draw_calls ↓

What diff_draw_calls does on Renderdoc

AI agents call diff_draw_calls 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 diff_draw_calls needs a policy

This tool inspects and compares existing GPU frame capture data to identify differences between two draw calls. It performs analysis and retrieval without creating, modifying, deleting, or executing arbitrary code. The operation is purely informational and has no side effects on the captured data or system state.

From the tool's definition Tool compares and returns state differences between two draw calls; no modifications, deletions, or external operations are performed. Description states 'return their state differences' indicating a read-only query operation.

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

How to control diff_draw_calls

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 diff_draw_calls:

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

diff_draw_calls 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 diff_draw_calls

What does the diff_draw_calls tool do? +

Compare two draw calls and return their state differences. Useful for understanding what changed between two similar draw calls. Args: eid1: Event ID of the first draw call. eid2: Event ID of the second draw call. 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 diff_draw_calls? +

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

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

Can I rate-limit diff_draw_calls? +

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

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

diff_draw_calls 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.