Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
cuda-mcp
MCP serversCUDA MCP: 20 real tools to read, check, lint, scaffold, build and run CUDA code.
@mrfentmen/cuda-mcp@1.0.0 -
cuda4cpu
MCP serversCompile, run and check CUDA and HIP kernels without a GPU: wrong results, races, memory errors
ghcr.io/javier-cabezas/cuda4cpu:0.6.0 -
NVIDIA CUDA Docs
MCP serversSearch NVIDIA CUDA documentation and code samples from AI coding agents.
-
CUDA-Q Docs
MCP serversCUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version.
cudaq-docs-mcp@0.1.1 -
Audio Studio
MCP serversLocal AI BGM and sound effects with Stable Audio 3 (Apple Silicon MLX, NVIDIA CUDA)
audio-studio-mcp@1.1.1 -
z-image-studio
MCP serversA Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
git clone https://github.com/iconben/z-image-studio.git -
TRELLIS-Studio
MCP serversLocal 3D asset studio powered by TRELLIS.2 and UniRig: image-to-3D, rigging, animation, PBR exports, game preparation, REST API and MCP.
git clone https://github.com/yoslo59/TRELLIS-Studio.git -
GPUvec
MCP serversCompare GPU specs and cloud rental offers, check CUDA support, and estimate Qdrant resources.
-
forge-mcp-server
MCP serversTurn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.
@rightnow/forge-mcp-server@1.0.2
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.