MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.
MIT ★ 173 -
MCP server serving NVIDIA CUDA-Q documentation, API reference, and runnable examples to AI agents, version-pinned to your installed cudaq.
pypi Apache-2.0 -
MCP server serving NVIDIA CUDA-Q docs, API reference, and runnable examples to AI agents, version-pinned to your installed cudaq
Apache-2.0 ★ 1 -
Train PyTorch on every GPU you can reach: one Trainer, from your laptop to many machines. NVIDIA CUDA, Apple Metal and CPU; self-hosted, open source.
pypi Apache-2.0 -
Denpex MCP Server: Diagnose GPU & ML training failures (CUDA OOM, NCCL timeouts, NVIDIA Xid, Slurm, vLLM) from Claude Desktop, Cursor, Windsurf, and Cline.
-
@rightnow/forge-mcp-servergithub.com/rightnow-ai/forge-mcp-serverupdated this year
MCP server for Forge GPU kernel optimization — generate and optimize Triton/CUDA kernels on real H100/A100 GPUs from any AI coding agent
npm MIT -
Engramgithub.com/Artemarius/Engramupdated this year
GPU-accelerated local semantic code index for Claude Code. CUDA-powered embeddings, HNSW vector search, tree-sitter AST chunking, MCP server — sub-3ms queries, fully on your machine.
★ 1 -
A CLI tool to verify and fix AI/ML environment compatibility (Driver <-> CUDA <-> Wheels) with platform-specific installation guides.
pypi MIT License -
⚡ MCP Server & API for real-time B2B buying signals, tech stack adoption (Rust, vLLM, CUDA) & AI SDR pitch angles from top AI companies.
-
MCP server generating coherent 16 kHz mixed audio scenes from text - speech, music, sound effects and ambience in one pass - powered by MiDashengLM-Gen (Xiaomi Research). Local-first, runs entirely on your CUDA GPU. Apache-2.0.
Apache-2.0 ★ 2 -
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
MIT ★ 4 -
Our participation to the 2025 Gradio Agent MCP Hackathon
MIT ★ 13 -
Agentic toolkit for building and optimizing high-performance inference engines tailored to your GPU and desired LLM.
pypi Apache-2.0 ★ 48 -
A multi-interface (REST and MCP) server for automatic license plate recognition
pypi MIT -
LLM-friendly API cards, an MCP server and a GPU benchmark for CuPy and nvmath-python (cuBLAS, cuFFT, cuSOLVER, cuSPARSE, cuDSS, cuTENSOR)
MIT -
Semantic search for your vault and code, through the CLI or MCP. Inference runs on your GPU.
MIT ★ 2 -
Local, calibrated decision engine for coding agents: laya.cpp as an MCP server plus skill, installed in one command.
MIT -
Cooperative GPU queue for people and AI agents: one line per card, heartbeats, polite yields, MCP server. Home on Codeberg.
MIT -
Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.
pypi MIT License -
Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.
WTFPL ★ 3 -
Sovereign local-first AI voice studio. Neural speech synthesis, zero-shot voice cloning, zero-latency dictation, and MCP agent voice I/O. Built with Tauri & FastAPI.
AGPL-3.0 -
engramgithub.com/staticroostermedia-arch/engramupdated this year
Geometric agent memory for Agents: 8-tool lean contract, harness injection at wake, session handoff. 79 MCP tools. Not a vector DB. Rust + MCP.
AGPL-3.0 ★ 21 -
🎙️ Fully-local voice for a whole crew of Claude Code sessions on Windows — multi-session, multi-language, multi-voice, one-command install.
MIT -
Find the hot kernel, cool it down: an Nsight/SASS MCP server with a verify-and-record contract and a kernel-speedrun loop for coding agents. Claude Code, Codex, any MCP client.
Apache-2.0 -
A 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)
Apache-2.0 ★ 128 -
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
MIT ★ 670 -
FIREFIGHTER: the coordinator and scheduler for unmanaged AI agents. Your AI agents won't set your GPU on fire. Or your CPU, your RAM, or your network. Claude Code, Codex, Gemini, Cursor, Kimi and more; MCP server; Windows/macOS/Linux.
MIT