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.
-
BDB Hardware & PCB — KiCad + OpenSCAD MCP servers and AI-era skills for schematic capture, PCB layout/routing, DFM sign-off, and parametric 3D enclosure design
npm Apache-2.0 -
linux-hardwaregithub.com/lspecian/linux-hardwareupdated this year
Hands-on bash lab for Linux internals, networking, and debugging. Homelab reference with seven topic dirs (PCIe/IRQs, disk I/O, network stack, memory, perf, app debugging, network debugging) plus an MCP server.
MIT -
Hardware-in-the-Loop (HIL) automation gateway and FastMCP server for embedded target boards
Apache-2.0 ★ 4 -
SpecTrust: The neutral, multi-vendor hardware trust & compatibility layer for AI agents
-
AI-Defined Hardware: DCL hardware OS on ESP32-S3 & STM32H723. Deterministic 100us ISR engine (route-table = process-table), 17/34 primitives, double-buffered hot-reload, Lua 5.4, MCP server (54 tools), IEC 61131-3 DSL compiler + Web IDE. Research, not a product.
MIT -
MCP server for FPGA hardware design in C⏚ - agents write a C-like HDL; the server compiles, checks, generates Verilog and synth-checks against the real toolchain.
pypi MIT ★ 1 -
Agent-agnostic harness that takes a hardware spec to a verified prototype — any AI coding agent, any OS. Deterministic and human gates keep every step auditable.
-
train-in-silencegithub.com/hlpun/train-in-silenceupdated this year
LLM fine-tuning hardware planner with CLI and API.
pypi MIT -
regennexus-mcpgithub.com/ReGenNow/regennexus-mcpupdated this year
MCP server for RegenNexus UAP - AI-controlled hardware for any MCP-compatible client
MIT -
MCP server that gives AI tools visibility into connected USB hardware
MIT -
MCP-based system stats tools for local hardware and performance monitoring
MIT -
AI-native EDA environment — MCP server for hardware design and verification
pypi AGPL-3.0-only -
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标 MCP：USB HID 控制与语音听写，需要兼容的 uMouse 设备与固件。
MIT ★ 404 -
Shared terminal sessions for humans and AI agents, starting with serial and hardware debugging.
Apache-2.0 ★ 151 -
axongithub.com/rudraptpsingh/axonupdated this year
Local hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.
MIT ★ 9 -
12-channel USB-C servo controller, Pololu Maestro compatible, MCP server for AI agents. Open hardware, CH32V203 RISC-V
MIT ★ 1 -
MCP server that lets AI agents build, flash, and monitor ESP-IDF projects on real hardware
MIT ★ 1 -
AI-Defined Hardware (ADH) — ESP32-S3 Task VM: firmware executes JSON tasks over MQTT, controlled by Claude via MCP Server
MIT -
Let your coding agent develop firmware on the real board, with the hardware as the gate.
pypi Apache-2.0 ★ 26 -
Judge hardware timing, serial boot logs and decoded traces against YAML contracts. pass/marginal/fail with evidence. MCP server, pytest plugin, GitHub Action.
MIT -
MCP server for EOSL.ai — source-backed hardware end-of-life (EOL/EOSL) lookups by part number; every date links to the vendor's own bulletin
Apache-2.0 ★ 1 -
Real, deterministic MCP server for PC no-boot/no-display troubleshooting -- real beep-code tables, no LLM guessing at hardware causes.
MIT ★ 1 -
Real, deterministic MCP server for PC no-boot/no-display troubleshooting -- real beep-code tables and a rule-based diagnostic sequence, no LLM guessing at hardware causes.
pypi MIT -
MCP server that lets AI agents debug STM32 firmware on real hardware (GDB + OpenOCD/ST-Link/J-Link): HardFault triage, FreeRTOS, SWO/RTT, decoded structured results.
MIT ★ 4 -
Tiny Windows service that serves a live hardware dashboard (CPU, every NVIDIA GPU, RAM, temperatures, fans) to any browser on your network, with an MCP server for AI agents and mod support
MIT ★ 2 -
Hardware-adaptive local LLM & cloud cascading gateway. Sub-5ms intelligent routing, 3-token lookahead failover, asymmetric verification, 1-click IDE config, and MCP for $0 token cost.
MIT ★ 4 -
bubbaloopgithub.com/kornia/bubbaloopupdated this year
Open-source Hardware AI agent. Single Rust binary for cameras, sensors, robots, and IoT fleets — orchestrated by AI agents with memory and real-time telemetry. Runs on Jetson, Raspberry Pi, any Linux.
Apache-2.0 ★ 30 -
Desktop app for ChipWhisperer hardware: live waveforms, capture, CPA, glitch sweeps, UART/SPI/JTAG/SWD interfaces, a logic analyser, firmware code on the power trace, notebooks, firmware builds and an MCP server
pypi Apache-2.0 -
Give AI hands to touch silicon — an MCP server for SEGGER J-Link, OpenOCD and Black Magic probes. Flash, halt, step, stream RTT logs and decode ARM Cortex-M faults. Verified against real hardware.
npm MIT ★ 43 -
Safe I/O harness for LLM agents: serial, Modbus TCP, MQTT, file sandbox and ESP32 flashing behind an MCP server, with a JSONL audit journal - plus ironbench, a pass@k benchmark for firmware agents on Wokwi/Renode/real hardware.
MIT ★ 2 -
Open-source control for the Velleman PS3005D lab power supply on Windows and Linux: GUI with live graphs and step sequences, CLI, and an MCP server so AI agents can drive the supply during hardware testing.
MIT ★ 1 -
Desktop app for ChipWhisperer side-channel and fault-injection hardware: live waveforms, capture, CPA, glitch sweeps, UART/SPI/JTAG/SWD interfaces, a logic analyser with protocol decoders, firmware code mapped onto the power trace, notebooks, one-click firmware builds and an MCP server for AI agents. Linux, Windows, macOS.
Apache-2.0 ★ 27 -
Disposable sandbox computers for ChatGPT, running on your hardware.
npm MIT -
Remote MCP server for Proxmox VE clusters and BMC-managed hardware.
NOASSERTION ★ 3 -
A collection of MCP (Model Context Protocol) servers for various hardware and data interfaces.
Apache-2.0 ★ 1 -
vektor-slipstreamgithub.com/vektor-memory/vektor-memoryupdated this year
Hardware-accelerated persistent memory for AI agents. Purchase and download at vektormemory.com
npm SEE LICENSE IN https://vektormemory.com/product -
tactus-mcpgithub.com/projectailiberation/tactusupdated this year
A content-agnostic MCP server that exposes intimate hardware control to AI agents by wrapping Buttplug/Intiface.
npm Apache-2.0 -
attestable-mcp-servergithub.com/kontext-security/attestable-mcp-serverupdated this year
Verify that any MCP server is running the intended and untampered code via hardware attestation.
★ 22 -
autonomogithub.com/gtfodevs/autonomoupdated this year
Tired of 'it works' lies? Autonomo MCP makes your AI prove it—on real hardware, right in your editor.
NOASSERTION ★ 36 -
🖥️ Disposable sandbox computers for ChatGPT, running on your hardware
MIT ★ 2 -
Hardware-Aware Hugging Face Discovery, Memory Fitting, Empirical Benchmarking & Swappable Local Model Gateway for AI Agents
★ 1 -
AiBridgeMCP — Core MCP Server Engine for ESP32 & Hardware Integration
★ 2 -
Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.
NOASSERTION ★ 4 -
Hardware-anchored DeFi MCP server (defensive security tool). GSD-planned rebuild of vaultpilot-mcp.
NOASSERTION -
Scalebrowserno update data
Scalebrowser is self-hosted browser infrastructure for AI agents. It gives each agent a persistent, isolated identity, keeps logins and passkeys intact, handles captchas and verification, and runs on hardware you control.
smithery -
tactusgithub.com/ProjectAILiberation/tactusupdated this year
Content-agnostic MCP server that lets any AI agent control intimate hardware via Buttplug/Intiface — safety layer on by default.
Apache-2.0 ★ 3 -
TokenMark MCP server: expose local-LLM benchmark configs + hardware-aware model recommendations to Claude and other agents.
npm MIT -
Read-only MCP server for VMware ESXi: CPU Ready, disk latency, snapshots, real space usage, hardware health and events
pypi MIT -
stratagithub.com/agenerationforwordz-tech/strataupdated this year
Self-hosted AI memory server. Your thoughts, your hardware, your data. Runs on a Raspberry Pi 4B.
NOASSERTION ★ 6 -
A type system, state validator, and safety firewall between AI coding assistants and physical instruments — schema-driven, MCP-native, zero hardware knowledge in the engine.
MIT ★ 1 -
strata-mcp-servergithub.com/agenerationforwordz-tech/strataupdated this year
Self-hosted AI memory server. Persistent memory on your hardware, not the cloud.
npm SEE LICENSE IN LICENSE -
webauthn-mcpgithub.com/pccr10001/webauthn-mcpupdated this year
A WebAuthn soft token simulator MCP for penetration testing and automated testing. This tool allows you to simulate WebAuthn authenticators (security keys, passkeys) for testing purposes without requiring physical hardware.
GPL-3.0 -
MCP server: let AI assistants read your car via ELM327 - DTCs, live data, freeze frame, VIN. Mock vehicle included, no hardware needed.
MIT ★ 2 -
Remote MCP server and agent skill for Local AI Picks: open-weight models that fit your hardware
MIT -
Persistent memory for AI agents over MCP — SQLite + FTS5 (BM25). No external infra, runs on your own hardware. MIT.
MIT ★ 1 -
vaultpilot-mcpgithub.com/szhygulin/vaultpilot-mcpupdated this year
Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.
npm BUSL-1.1 -
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 -
Cortex-agents_infragithub.com/kth3/Cortex-agents_infraupdated this year
The High-Performance, Hardware-Adaptive Knowledge Engine for MCP Agents: Hybrid Graph-RAG & Atomic Concurrency Control.
MIT ★ 2 -
Benchmark local LLM inference speed (tokens/sec) on your own hardware — llama.cpp native + cloud APIs, 124-model catalog, optimal-quant picker, and an MCP serve mode.
MIT ★ 2 -
MCP server that lets AI coding agents add smart-glasses capabilities to Android and iOS apps — scaffold, validate, and simulate before touching hardware
MIT ★ 2