Get vertex input layout and buffer bindings at the current event. Shows vertex attributes (name, format, offset), vertex buffer bindings, and index buffer. Args: event_id: Optional event ID to navigate to first.
AI agents call get_vertex_inputs 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.
This tool retrieves and queries GPU frame capture state information (vertex layout and bindings) for inspection and analysis purposes. It has no side effects beyond reading existing diagnostic data from a RenderDoc capture file. No data is created, modified, deleted, or financial operations performed. This is a straightforward read operation with minimal risk.
From the tool's definition Tool name 'get_vertex_inputs' and description 'Get vertex input layout and buffer bindings' indicate pure data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_vertex_inputs gives an agent:
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_vertex_inputs:
{
"version": "1",
"default": "deny",
"tools": {
"get_vertex_inputs": {}
}
}get_vertex_inputs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get vertex input layout and buffer bindings at the current event. Shows vertex attributes (name, format, offset), vertex buffer bindings, and index buffer. Args: 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.
Register the Renderdoc MCP server in PolicyLayer and add a rule for get_vertex_inputs: 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.
get_vertex_inputs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_vertex_inputs 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.
Set action: deny in the PolicyLayer policy for get_vertex_inputs. 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.
get_vertex_inputs 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.
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.