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.
-
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
figmin-mcp-gpuupdated this year
MCP bridge that connects AI Agents to Figmin XR for spatial computing AI collaboration (GPU TTS build)
pypi LicenseRef-Proprietary -
ai-compute-radaractive
MCP server bridge for AI Compute Radar: which open models fit your GPU or Mac (measured GGUF sizes + computed context cache), GPU rental prices from eight sources, model momentum, weekly pick. Read-only, no auth, no telemetry.
npm MIT -
Model Context Protocol tools for better-compute: pools, capacity, GPU reservations and node status for AI agents, gated by better-iam.
npm Apache-2.0 -
Compute Portal MCP server — 23 cp_ tools for agent-native GPU compute
npm MIT -
tnr-mcpgithub.com/thunder-compute/thundernetesupdated this year
Thunder Compute MCP server — manage GPU instances from AI coding agents
npm MIT -
pulse-mcpgithub.com/pulsebenchmarks/pulse-mcpupdated this year
Open compute-pricing MCP server — daily GPU and inference-token medians, CC-BY 4.0.
Apache-2.0 -
MCP server for checking compute and GPU availability across multiple servers
★ 1 -
runpod-blade-mcpgithub.com/groupthink-dev/runpod-blade-mcpupdated this year
RunPod GPU compute MCP server — pods, serverless endpoints, jobs, and GPU inventory with token-efficient defaults
npm MIT -
vultr-blade-mcpgithub.com/groupthink-dev/vultr-blade-mcpupdated this year
Vultr GPU compute infrastructure MCP server — VMs, bare metal, serverless inference, DNS, firewall, snapshots, billing with token-efficient defaults
npm MIT -
Model Context Protocol (MCP) Server for Kilawatt Cloud—enables Cursor, Claude Desktop, and AI agents to programmatically request and manage GPU compute nodes.
npm MIT -
krauncher-mcpupdated this year
MCP server: a pre-run GPU-task cost estimate (compute/setup/io on the reference card, VRAM/disk, what the analyzer read) as an agent tool. Static analysis only — the code is never executed.
pypi MIT -
Make funky shader loops, posters, FastSD images and 9:16 product video ads with Claude, on your own computer. One MCP server + Claude Code plugin. No cloud, no accounts, no NVIDIA GPU.
MIT ★ 1 -
math-mcpgithub.com/andylbrummer/math-mcpupdated this year
GPU-accelerated MCP servers for computational mathematics, physics simulations, and machine learning
pypi MIT ★ 2 -
Unlimited computation for agents. Results depend on your equipment; GPU optional.
pypi -
Jupyter Lab MCP server for SLURM clusters — run GPU code on compute nodes from Claude Code
-
Computer use for every Windows app window, for any MCP agent: GPU-rendered, covered or in the background. UI Automation tree, capture fallback chain, OCR, background input.
pypi Apache-2.0 -
parallelix-mcpgithub.com/parallelixnetwork/parallelix-mcpupdated this year
MCP server for the ParalleliX Compute API. Offload parallel inference sub-tasks to a distributed GPU network, paid in $PRLX credits.
npm MIT -
Desktop Commander-parity remote MCP plus a device mesh that pools compute, GPU, RAM and disk across your own machines.
pypi MIT -
dcp-mcpgithub.com/dhnpmp-tech/dcp-mcpupdated this year
DCP MCP server — run sovereign in-Kingdom inference, rent GPUs, and manage storage on DCP (Saudi Arabia's sovereign AI compute platform) from any MCP agent. Thin client over https://api.dcp.sa.
MIT -
Image Annotation, including Histopathology slides; From H&E slide to training data in one conversation: nuclei, outlines and slide QC, exported to QuPath, COCO or YOLO. No GPU needed. For Whole Slide Imaging (WSI), Digital and Computational Pathology, Bioinformatics, Tumor Microenvironment (TME) and MLOps Data Labeling.
pypi MIT -
lean-memorygithub.com/joinQuantish/lean-memoryupdated this year
Lean on-device memory search for AI agents. Fork of QMD optimized for VPS/headless compute — no GPU, no 2GB model downloads.
★ 1 -
learn-mcpgithub.com/fvegiard/learn-mcpupdated this year
AI Engineering Learning Reference MCP Server — 550+ searchable references for MCP, RAG, agents, fine-tuning, MLOps, prompt engineering, inference, vector DBs, GPU compute, autonomous agents, and Claude Code workflows
MIT -
AI-native quantum computing SDK — PyTorch QuantumLayer & Continuous Resonance, Apple Silicon Metal/MLX GPU engine, 23 MCP tools, Willow dynamic QEC, 200+ qubit MPS
pypi Apache-2.0 -
Private, local audio and video transcription for Claude: an MCP server that runs Whisper on your computer, on the GPU or CPU, with text, SRT subtitle, or JSON output. Works with Claude Desktop, Claude Code, and claude.ai.
mcpb MIT ★ 1 -
Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.
npm AGPL-3.0 ★ 422 -
Free daily GPU rental price index (H100, H200, A100, B200, B300, RTX PRO 6000) and AI token price index. Website, MCP connector for Claude and ChatGPT, CC BY 4.0 data.
NOASSERTION ★ 1 -
GPU molecular docking service (AutoDock-GPU + AutoGrid) for the NovoMCP engine
Apache-2.0 -
Autonomous GPU placement recommendation & routing engine for AI agents — ranks live RunPod GPU offers, pay per call via x402/USDC on Base or a prepaid key.
npm MIT -
Official Model Context Protocol (MCP) server and high-level verifiable AI primitives for distributed GPU matrix multiplication
pypi Apache-2.0 -
GPU molecular-dynamics service (GROMACS) for the NovoMCP engine.
Apache-2.0 -
MCP server for leasing and running on Prism Network GPUs.
npm Apache-2.0 -
@ister/mcpactive
MCP server for Ister's GPU price indices: an AI assistant reads the Ister API (/v1) with your own API key. Read-only.
npm MIT -
Beam — a small, fast CPU+GPU ray tracer in Go with POV-Ray parity tooling, glTF/OBJ/STL import, extruded text, and an MCP server for AI-driven scene authoring
GPL-2.0 -
modal-sandbox-mcpgithub.com/amichae2/modal-sandbox-mcpupdated this year
MCP server that runs Python on Modal cloud hardware (CPU/RAM/GPU) — for Open WebUI and other MCP clients
MIT -
@dispersed/mcp-serverupdated this year
Model Context Protocol server for the Dispersed Network compute API
npm MIT -
cnx-mcpupdated this year
Local MCP stdio bridge for cnx — GPU rental negotiation agent (proxies to the live cnx /mcp HTTP endpoint, zero local business logic)
pypi MIT -
Command-line interface and Python SDK for VoltageGPU: confidential GPUs on demand (Intel TDX, tenant-side NVIDIA attestation) and an OpenAI-compatible inference API, billed per second.
MIT ★ 1 -
Read-only MCP server for GPU rental price data, metered per-call via x402 (USDC on Base). No API key, no signup. Live endpoint: https://rentgpu.link/mcp
MIT -
CLI, library, and MCP server for signing, hash-chaining, and verifying compute usage receipts across any provider.
go Apache-2.0 -
Green (GRN): an open compute network secured by proof of compute. Miners multiply matrices for AI; anyone, including an AI agent, buys that compute with GRN.
MIT ★ 1 -
Correctness-gated, LLM-driven GPU kernel optimization on the Raspberry Pi 5's V3D GPU. The model proposes; a Burr state machine served over MCP verifies against physics gates, benchmarks, and decides.
MIT -
MCP server for GPUlinks — let AI agents join the global personal-GPU network, post to the agent board, and inspect the cluster.
npm MIT -
Typed, reproducible high-content microscopy workflows across GUI, Python, CellProfiler, Napari/Fiji, GPU, and local MCP agents.
pypi MIT ★ 7 -
BitPull (bitpull.cloud): share signed, AI-readable code, computing power and open AI models with AI tools through MCP. CLI and MCP server.
npm UNLICENSED -
runpod-cowork-plugingithub.com/Angelus174/runpod-cowork-pluginupdated this year
RunPod MCP plugin for Claude and Cowork. Manage GPU pods, Jupyter environments, AI jobs, and cloud inference workloads through natural language.
MIT -
fortranspiregithub.com/maurinl26/fortranspireupdated this year
A 100% Private MCP Coding Assistant and Scientific Porting Pipeline
pypi Apache-2.0 -
servprivacy-mcpgithub.com/ServPrivacy/servprivacy-mcpupdated this year
MCP server for ServPrivacy - deploy KYC-free, crypto-paid offshore VPS, dedicated, Windows RDP and GPU AI servers from any AI agent.
pypi MIT ★ 1 -
Universal experiment provenance and reproducibility for science and engineering.
npm Apache-2.0 -
genie-lockergithub.com/nhantour/genie-lockerupdated this year
Read-only MCP connector and public API for quality-gated, ephemeral private AI inference.
oci MIT -
Make your model serve faster on your GPU, and prove it. Skills for Claude Code, Codex and OpenCode, plus a CLI and MCP server: your agent picks and tunes inference engines, can write GPU kernels, and backs every number with client-timed benchmarks, anti-cheat gates and quality checks.
pypi Apache-2.0 -
Distributed document RAG with VRAM-aware workload placement across heterogeneous nodes. Four interfaces: CLI, API, MCP, Web UI.
MIT ★ 6 -
Run research on the NRP Nautilus cluster from your AI assistant: a local MCP server that plans, runs, watches and cleans up Kubernetes workloads safely, as you.
go MIT -
MCP server for Gate402: pay-per-call agent APIs over x402. Open-model LLM inference, Base trading data, SEC filings and web scraping. 20 tools, free tier, no signup.
npm MIT ★ 1 -
Lets an AI assistant set up and run AI training on rented computers, with spending limits in the code.
MIT -
SiliconCote by OutilsIA: native Rust app that collects and dates AI hardware prices on your computer. MCP tools included. Windows, Linux.
-
MCP server for Lighter perpetuals, including the H100 compute-price market. Built by Prism. Not affiliated with, endorsed by, or operated by Lighter or elliottech.
npm Apache-2.0 -
Local-first MCP server for BeamNG.drive, BeamNGpy, Lua extensions, and GPU vision
MIT ★ 2 -
capix-mcpgithub.com/capix-protocol/capix-mcpupdated this year
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.
npm Apache-2.0 -
Native 3D scene editor with GPU rendering, keyframe animation, MCP tools and an authenticated local HTTP API.
NOASSERTION