"wgpu" matching MCP servers:

Exposes NVIDIA GPU metrics (info, utilization, VRAM, temperature) via MCP tools for real-time querying from AI assistants.

Enables recording a Wine or macOS program on an Apple silicon Mac and analyzing its GPU usage — GPU milliseconds per frame, frame pacing, FPS and memory — through Instruments' Metal System Trace, and also reads Metal .gputrace captures without Xcode and reports Apple's published GPU family facts. Recording, listing, comparing, and paging through traces and captures are exposed as tools that a shell or an AI coding agent can call directly.

MCP server for AI-controlled GPU VRAM management in ComfyUI, allowing Claude to monitor and control GPU state, manage model offloading, and start/stop ComfyUI.

Enables AI agents to submit GPU job requests, select eligible workers, track execution, and retrieve results via MCP.

Enables AI agents to run GPU acceptance tests on NVIDIA nodes you administer over SSH, executing DCGM diagnostics, a CUTLASS GEMM benchmark, HBM and PCIe bandwidth tests and NCCL all-reduce, then reporting each measurement against the matching profile's thresholds. Supports creating tests, tracking progress, sharing reports, and requires two owner-only confirmations before nodes are added or a test starts.

Enables MCP clients to discover NVIDIA, AMD, and Intel GPUs, monitor utilization, memory, temperature, power, clocks, and processes, retain bounded local history, and estimate whether AI models fit available VRAM before loading them.

An MCP server that enables AI agents to query real-time NVIDIA GPU metrics like utilization, memory, temperature, and power without external monitoring tools.

Provides read-only visibility into local CPU pools and Apple GPU lane usage inside Claude Code and Codex.