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.
-
Hardware-in-the-Loop (HIL) automation gateway and FastMCP server for embedded target boards
Apache-2.0 ★ 4 -
hardcigithub.com/hp-8472/hardciupdated this year
Safe local hardware-in-the-loop bridge for AI-assisted embedded CI loops
pypi Apache-2.0 -
MCP server that lets AI agents drive an EmbeddedCI BenchPod hardware-in-the-loop bench
pypi Apache-2.0 -
BenchPod plugins for Claude Code, Codex and Claude Desktop: drive a hardware-in-the-loop bench from your AI agent
Apache-2.0 -
xovis-sdkgithub.com/xovis-open-sdk/xovis-sdkupdated this year
Unofficial Xovis Hardware integration via MCP that seamlessly bridges the Xovis Python SDK to autonomous AI agents. Features zero-trust pseudonymization, human-in-the-loop safety guardrails, and unlocks the full suite of 261 tools (including analytics, da
npm MIT -
AIMG-AI-based_Media_Generatorgithub.com/MartinKhadjo/AIMG-AI-based_Media_Generatorupdated this year
Local-first, cloud-ready, model-agnostic AI media generation platform: runs 14B video models on a 12 GB laptop GPU, auto-integrates new models hardware-aware, directs clips and multi-scene commercials via LLM with human-in-the-loop approval, enforces quality gates and a server-side budget guard, fully orchestrable by AI agents via MCP.
-
HILgithub.com/adwuard/HILactive
Hardware Testing in Loop CLI Testing Instruments. "Build-Flash-Debug-Test and Loop!"
★ 2 -
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.
-
Physical camera perception, measurement, and verification tool for MCP AI agents
pypi MIT -
Let your coding agent develop firmware on the real board, with the hardware as the gate.
pypi Apache-2.0 ★ 26 -
devsignalgithub.com/JacobBeningo/devsignalupdated this year
Signal generator control for the embedded bench — CLI + MCP server for AI agents (Siglent SDG series)
MIT ★ 3 -
embedded-ai-workspacegithub.com/atillab1/embedded-ai-workspaceupdated this year
Three-phase Claude tooling for embedded firmware: MISRA Skill + Datasheet MCP + HIL pipeline. Verified end-to-end on STM32F4-DISCOVERY hardware.
MIT ★ 6 -
devusbgithub.com/JacobBeningo/devusbupdated this year
USB power control for the embedded bench — CLI + MCP server for AI agents (Yepkit YKUSH hubs)
MIT ★ 6 -
devpsugithub.com/JacobBeningo/devpsuupdated this year
Bench power supply control for the embedded bench — CLI + MCP server for AI agents (B&K Precision 168xB / Manson HCS)
MIT ★ 3 -
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.
pypi MIT ★ 4 -
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 -
yebo-mcp-serverupdated this year
Yebo MCP Authorization Server — add hardware-bound human authorization to any AI agent in one line
npm MIT -
@yebo-auth/mcp-serverupdated this year
Yebo MCP Authorization Server — add hardware-bound human authorization to any AI agent in one line
npm MIT