hwprobe-mcp
Hardware probe MCP server that provides deep hardware inventory and live sensor telemetry for AI agents, including CPU, memory, disk, GPU, and sensor data across platforms.
README
hwprobe-mcp
A hardware probe for AI agents, over MCP.
hwprobe-mcp is a Model Context Protocol server that gives an
AI agent (any MCP client) both deep hardware inventory and
live sensor telemetry through a small set of clean, JSON-returning tools.
Most "system monitor" MCP servers are thin psutil wrappers that only report utilization. hwprobe-mcp
deliberately fuses three layers so an agent gets the whole picture in one place:
| Layer | Backends |
|---|---|
| Cross-platform core | psutil — CPU/mem/disk/net + component temps, fans, battery |
| Rich Linux sensors | sensors -j (lm-sensors) — temperatures, fan RPM, voltages, power |
| Deep inventory | lscpu -J, lsblk -O -J, dmidecode, lspci (Linux) · system_profiler -json (macOS) · CIM/WMI (Windows) |
| Devices | nvidia-smi (GPU inventory + telemetry) · smartctl -j (disk SMART: model, temp, health, hours) |
Everything degrades gracefully: a missing tool, an absent GPU, or a lack of root privileges becomes a
warnings[] entry, never a crash.
Tools
| MCP tool | What it returns |
|---|---|
hardware_inventory |
Static deep inventory — CPU model/cores/arch/cache, RAM + DIMM layout, disks (model/serial/size), GPUs, motherboard/BIOS, OS/platform. |
live_sensors |
Live snapshot — CPU/component temperatures, fan RPM, battery, plus voltages/power (via lm-sensors) and NVIDIA GPU temp/power/util. |
cpu_status |
CPU identity + live per-core utilization %, per-core frequency, load average, core temperatures. |
gpu_status |
GPU inventory + live telemetry (NVIDIA via nvidia-smi: temp, util, power, clocks, memory). |
disk_health |
Per-disk SMART: model, serial, firmware, capacity, temperature, SMART pass/fail, power-on hours, power cycles. |
system_snapshot |
Everything above in a single call — the "tell me everything about this machine" tool. |
check_dependencies |
Which optional backends are installed vs missing, what each unlocks, and the exact command to install any missing one (auto-detects the package manager). |
Every tool returns a consistent envelope:
{
"ok": true,
"platform": "Linux",
"sources": ["psutil", "lm-sensors"],
"warnings": ["nvidia-smi: NVIDIA driver not loaded"],
"data": { "...": "..." }
}
Install
Requires Python 3.10+.
# from source (until published to PyPI)
git clone git@github.com:notreallycheeks/hwprobe-mcp.git
cd hwprobe-mcp
pip install -e .
For the fullest data on Linux, install the native helpers (all optional):
sudo apt install lm-sensors smartmontools pciutils util-linux dmidecode
sudo sensors-detect --auto # one-time, sets up lm-sensors
NVIDIA GPU telemetry uses the
nvidia-smibinary shipped with the NVIDIA driver — there is no pip extra to install.
Checking what's installed
hwprobe works with whatever is present and degrades gracefully — but it will also tell you what's missing and how to install it. Run the built-in doctor:
hwprobe-mcp --doctor
...or have your agent call the check_dependencies tool. Each missing backend comes with the
exact install command for your platform's package manager, and the JSON-returning tools embed the
same hint in their warnings.
Two backends need elevated privileges to return data — smartctl (disk SMART) and
dmidecode (motherboard/BIOS/DIMM). Run the server as root, or grant scoped passwordless
sudo just for smartctl so disk_health works from the unprivileged server:
echo "$USER ALL=(root) NOPASSWD: $(command -v smartctl)" | sudo tee /etc/sudoers.d/hwprobe-smartctl
sudo chmod 0440 /etc/sudoers.d/hwprobe-smartctl
hwprobe automatically uses sudo -n smartctl when it isn't root, so no code changes are needed.
Use with an MCP client
Add it to your MCP client's server config:
{
"mcpServers": {
"hwprobe": {
"command": "hwprobe-mcp"
}
}
}
Then ask your agent things like "what's this machine's CPU and how hot is it right now?" or "check disk SMART health and current GPU power draw."
Try it without an MCP client
--selftest runs every collector and dumps the JSON an agent would see — handy for verifying your
box and for CI:
# from the repo root, before install:
PYTHONPATH=src python -m hwprobe_mcp --selftest | jq .
# or, once installed (pip install -e .):
hwprobe-mcp --selftest
Platform support
| Capability | Linux | macOS | Windows |
|---|---|---|---|
| Inventory (CPU/mem/disk/GPU/OS) | ✅ full | ✅ (system_profiler) | ✅ (CIM/WMI) |
| Component temps / fans | ✅ psutil + lm-sensors | ⚠️ limited | ⚠️ needs LibreHardwareMonitor |
| Voltages / power | ✅ lm-sensors | ⚠️ | ⚠️ |
| Battery | ✅ | ✅ | ✅ |
| NVIDIA GPU telemetry | ✅ | — | ✅ |
| Disk SMART | ✅ (root) | ✅ (root) | ✅ (admin) |
Note: deep motherboard/BIOS/DIMM inventory (
dmidecode) and full SMART data need root/admin. Without it,hwprobe-mcpreturns everything it can read and flags the rest inwarnings.
Roadmap
- [ ] Windows deep sensors via a bundled LibreHardwareMonitor bridge
- [ ] macOS
powermetricspower/thermal integration (opt-in, needs sudo) - [ ] AMD/Intel GPU telemetry (
rocm-smi,intel_gpu_top) - [ ] Optional streaming/
subscribetool for continuous sensor sampling - [ ] Publish to PyPI +
uvx hwprobe-mcp
License
MIT © 2026 notreallycheeks
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。