MCP servers tagged gpu
66 live MCP servers tagged "gpu", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with gpu.
Lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
gpartin/WaveGuardClient
Python SDK for WaveGuard physics-based anomaly detection API. One call. Any data.
Harness Terminal
Native macOS terminal with GPU rendering, durable sessions, coding-agent workflows, and SSH connectivity. Session host, daemon, and CLI support Linux; optional MCP and AI summarie…
Kubeledger
System of Record for Kubernetes cost accounting: per-namespace CPU, memory and GPU usage, with the 30% non-allocatable overhead made visible. Connects to AI assistants via MCP (Cl…
AutoMegaKernel
An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/ab…
Regenerating-World/pix-mcp
MCP server for debugging DirectX 12 apps with Microsoft PIX
Global Capacity Orchestrator On AWS
AI/ML and HPC at planetary scale. One API. Every Accelerator. Any Region. MIT-0 licensed
Nosana MCP
Nosana MCP: let AI agents rent GPUs on Nosana and deploy templates such as MiniMax H3 with account credits. MCP server + nosana-deploy CLI.
Shipyard
Shipyard 🚢 — Cross-platform Docker container management platform. Python FastAPI backend + Flutter frontend for Android, iOS, macOS, Web & OpenHarmony. Manage multiple Docker host…
Gflow
A lightweight, single-node GPU job scheduler implemented in Rust.
Lambda Cloud CLI
Lambda Cloud CLI tool with interactive TUI and MCP server for GPU instance management
Capix
Capix MCP Server — deploy and manage private LLM instances, compute, websites, and verified workloads on the Capix network from any AI coding agent that supports MCP.
Skiff Cloud
Sovereign Bare-Metal Cloud CLI, AI Agent SDK & Model Context Protocol (MCP) Server
Vastai MCP
MCP server + CLI to rent the cheapest Vast.ai GPU that can actually run the job (MiniMax H3, LTX-2.5, ComfyUI), and guarantee it gets torn down
Colab MCP Termux
Run the Google Colab GPU MCP server on Termux/Android: source-built pydantic-core + maturin, DNS-over-HTTPS fix, one-command installer. Call Colab T4/L4 from opencode, Claude Code…
Omarchy Nebius
Need a bigger GPU? Nebius cloud GPUs from Omarchy: capacity, VM launch, SSH, and Codex + Claude Code tools.
Deeplit MCP Server
Claude Code and Codex plugin for deeplit: manage GPU inference instances, volumes, models and billing from your coding agent, authorized by a scoped API key.
OpenMind
Pool your GPUs into a private AI cluster. Chat with sharded LLMs, generate images & videos across machines. Built on Odysseus + Hyperspace AGI + ComfyUI-Distributed.
NeuralForge
Fine-tune large language models on local hardware using a web interface with QLoRA training and GGUF export support.
AutoDL CLI
Agent-friendly CLI, MCP server and SDK for managing AutoDL GPU instances — create, boot, SSH, run and auto-shutdown, all scriptable. 用命令行和 MCP 管理 AutoDL GPU 实例。
AI Media Stack
Self-hosted multi-tenant AI media platform on one GPU: floor plan → 3D (glTF) → photoreal SDXL shots & 360° panoramas, room-photo declutter & redesign, voice-to-voice translation,…
ComfyUI Base
The shared toolchain for ComfyUI workflow packages on any NVIDIA GPU host: one installer, pinned packs, declared models from Hugging Face or GitHub, the boot, the driver, and Comf…
Autodl MCP
让 Cursor / Claude / Codex 一句话开 GPU、跑 ComfyUI 工作出片 — H3 文生视频 / 首尾帧 / IndexTTS2 配音，实例开关机不烧钱，13 工具 30 秒一行命令接入。Chat-to-video on rented GPUs, one-line install.
Flopsindex
Public, source-opaque reference-rate SDKs and MCP server for FLOPS compute price indices — every value carries a verify URL.
Gpu Perf Tune
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
Mnvitop
One terminal for the GPUs of all your ssh hosts, with an MCP server so agents can find a free GPU. The remote side needs only nvidia-smi.
Comfyui On Openshift
Stock ComfyUI for a whole team on one scale-to-zero GPU pool — cluster SSO, fair queueing, VRAM-tier routing, per-user showback with FOCUS chargeback, and GPU workers unreachable…
Datacenter MCP Server
Mission-critical data center engineering MCP server. 8 professional calculation tools for AI agents.
TokLedger
The local inference ledger -> a zero-dependency OpenAI-compatible proxy that prices every request your home GPU serves: tokens, TTFT, tok/s, kWh, local $ and cloud-equivalent cost.
Spraay Compute
💧 OpenClaw / Claude Code skill for AI agents: rent GPU compute, run AI model inference (LLM, image, video, speech, embeddings), and buy prepaid compute futures credits — paid in U…
Tandem Tokens
Local Ollama offload harness for Claude, Grok, Codex, and any MCP agent — map-phase on your GPU, digests only for premium tokens.
Junglegrid Examples
Example workloads, MCP prompts, CLI commands, and integration templates for running AI jobs on Jungle Grid.
Jungle-Grid/mcp-server
tuning, and batch workloads.
SebastianGilPinzon/colab-mcp
mcp with all tools visible at startup, OAuth GPU control, and Windows support.
Ollama Batch Processor
📚 Streamline text processing with the Ollama Batch Processor, a GUI tool for translation, audiobook formatting, and paraphrasing using Ollama LLM models.
Shader Linux Glsl
Linux GPU shader with MCP control from LLMs
Modal Sandbox MCP
MCP server that runs Python on Modal cloud hardware (CPU/RAM/GPU) — for Open WebUI and other MCP clients
Molla
Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.
Sonder Runtime
Sonder Runtime — private-first GPU-backed AI orchestration, grounded execution, web tools, memory, and adaptive learning.
Claude Colab
Give Claude Code GPU access via Google Colab — CLI + MCP server with E2E encryption
Nanos
Lightweight, process-isolated WebAssembly micro-runtime for sandboxed AI agents with native GPU (Metal & CUDA) offload
AUTODL PLUGIN
Safety-first AutoDL plugin for Codex with 26 typed MCP tools and documentation-aware skills
Magenticbrain Vllm Aspire
Run microsoft/MagenticBrain (14B) locally on GPU via vLLM (Docker), orchestrated with Aspire + the aichatweb RAG template.
Deepseek Harness Ssh
Safety-gated SSH development plugin for DeepSeek Harness and MCP, built for GPU and offline laboratory servers.
Step1X Edit Docker
🎨 Production-ready Docker deployment for Step1X-Edit with intelligent GPU management. Features: UI + API + MCP, lazy loading, instant offloading, multi-language support.
Ovis Image Docker
🎨 One-click Docker deployment for Ovis-Image 7B text-to-image model with Web UI, REST API, and MCP support
WebGPU
https://webgpu.777737777.xyz
Ash4d.com
Private AI platform on k3s — Ollama/Qwen3 + Milvus RAG + MCP agentic tooling + Fleet multi-cluster management
Io Net
io.net — independent third-party profile of a public API surface, by API Evangelist. io.net is a decentralized GPU network for AI compute, built on Solana, that aggregates idle co…
Xid R
Xid-R is an autonomous GPU compute broker that harvests idle GPU capacity and allocates it to AI agents. It uses MCP (Model Context Protocol) for tool integration and A2A (Agent-t…