Yamaru Hardware Probe
@yamaru-eu
Yamaru Hardware Probe gives Claude Desktop and other MCP clients real visibility into your machine. 10 expert tools: full hardware inventory, real-time performance & thermal monitoring, RAM pressure analysis, SMART storage health, antivirus impact diagnostics, and LLM compatibili
Overview
What is Yamaru Hardware Probe?
Open-source MCP server that gives LLM clients real hardware diagnostics from the machine they run on. It exposes 10 expert tools covering CPU, RAM, VRAM, thermals, storage health, and more — so AI assistants provide grounded, data-driven answers instead of generic responses. Built by the Yamaru project.
How to use Yamaru Hardware Probe?
Add the server configuration to your claude_desktop_config.json with the command npx -y @yamaru-eu/hardware-probe and restart Claude Desktop. The server then exposes 10 diagnostic tools queryable through any MCP client.
Key features of Yamaru Hardware Probe
- Deep hardware inventory — CPU, RAM, GPU, motherboard, OS
- Real-time performance monitoring with top processes
- Thermal and power diagnostics with throttling detection
- SMART storage health per-disk temperature and wear
- Antivirus and EDR impact detection on dev paths
- LLM compatibility prediction for quantization fit (BETA)
Use cases of Yamaru Hardware Probe
- Diagnose PC slowness during local model inference
- Check if your machine can run a specific LLM model
- Verify antivirus is not scanning your models folder
- Monitor system health over time for anomaly detection
- Tune Ollama, CUDA, or Metal inference runtime settings
FAQ from Yamaru Hardware Probe
What makes this different from asking an LLM directly?
Instead of a generic “it depends on your configuration” response, the server lets the LLM read your actual CPU, RAM, VRAM, thermals, and storage health and give you a real, data-driven answer.
What runtime dependencies are required?
The server runs via npx with @yamaru-eu/hardware-probe. It is built on TypeScript, the MCP SDK, and the systeminformation library.
How does the server handle privacy?
The server is privacy-first — it automatically anonymizes unique hardware IDs before any remote call.
What features are in BETA status?
The LLM compatibility prediction tools (check_llm_compatibility, get_llm_recommendations, analyze_inference_config) are marked as BETA.
What license is the project under?
The project is licensed under Apache 2.0.
