Scan all float render targets for negative/NaN/Inf pixels and trace their origin. Automatically identifies which draw calls first introduce negative values, checks if TAA/temporal buffers are amplifying them, and provides root cause candidates with fix suggestions. Args: check_targets: Optional l...
AI agents call diagnose_negative_values 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 inspects GPU frame capture data to identify and diagnose rendering issues. It reads render target states, traces draw call history, and provides analysis—all read-only operations that retrieve and analyze existing capture data. There are no writes, deletions, code execution, or financial operations. The tool operates entirely within the analytical domain of graphics debugging on pre-captured data.
From the tool's definition The tool 'diagnose_negative_values' performs analysis and scanning operations: 'Scan all float render targets for negative/NaN/Inf pixels and trace their origin', 'Automatically identifies which draw calls first introduce negative values', and 'provides root…
Risk signalsAdmin/system-level operation
Documented attack patterns abuse exactly the kind of access diagnose_negative_values 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 diagnose_negative_values:
{
"version": "1",
"default": "deny",
"tools": {
"diagnose_negative_values": {}
}
}diagnose_negative_values 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.
Scan all float render targets for negative/NaN/Inf pixels and trace their origin. Automatically identifies which draw calls first introduce negative values, checks if TAA/temporal buffers are amplifying them, and provides root cause candidates with fix suggestions. Args: check_targets: Optional list of render target resource IDs to check. If omitted, checks all floating-point render targets. trace_depth: How many events to scan backward when tracing the first event that introduced negative values (default 5). 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 diagnose_negative_values: 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.
diagnose_negative_values 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 diagnose_negative_values 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 diagnose_negative_values. 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.
diagnose_negative_values 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.