List all buffers in the capture. Args: min_size: Optional minimum byte size to filter by.
AI agents call list_buffers 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 enumerates buffer metadata from a GPU frame capture without modifying, executing operations on, or deleting any data. It is purely informational for graphics debugging analysis, consistent with other analysis tools in the RenderDoc suite (analyze_bandwidth, analyze_overdraw, etc.). No code execution, financial impact, or data mutation occurs.
From the tool's definition Tool name 'list_buffers' and description 'List all buffers in the capture' indicate a query/retrieval operation with no side effects. The optional 'min_size' parameter is a filter, not a modification.
Documented attack patterns abuse exactly the kind of access list_buffers 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 list_buffers:
{
"version": "1",
"default": "deny",
"tools": {
"list_buffers": {}
}
} list_buffers 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.
List all buffers in the capture. Args: min_size: Optional minimum byte size to filter by. 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 list_buffers: 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.
list_buffers 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 list_buffers 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 list_buffers. 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.
list_buffers 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.