
Hardware Probe
This server gives Claude direct access to your hardware telemetry and system diagnostics. It exposes tools like analyze_local_system for CPU/GPU/RAM inventory, thermal_profile for real-time temperature and throttling detection, and check_llm_compatibility for predicting whether a specific model will run locally. You'd reach for this when debugging performance issues, diagnosing thermal problems, or figuring out which quantized LLM fits in your VRAM. It also includes monitor_system_health for statistical tracking over configurable windows and diagnose_antivirus_impact for spotting EDR conflicts. Built on stdio transport with privacy-first design that anonymizes hardware IDs before any remote calls.
- GitHub stars
- 5
- tools
- 10
- transport
- STDIO
- env var
- 1
- last updated
- Apr 19, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
analyze_local_systemFull hardware inventory.
Full hardware inventory.
No parameter schema in public metadata yet.
analyze_performanceReal-time performance metrics and top processes.
Real-time performance metrics and top processes.
No parameter schema in public metadata yet.
analyze_ram_pressureDetailed memory pressure and RSS analysis for deep RAM troubleshooting.
Detailed memory pressure and RSS analysis for deep RAM troubleshooting.
No parameter schema in public metadata yet.
check_storage_healthDisk SMART health, firmware, and I/O bottleneck analysis.
Disk SMART health, firmware, and I/O bottleneck analysis.
No parameter schema in public metadata yet.
thermal_profileReal-time CPU/GPU thermal states, fan speeds, and frequency throttling detection.
Real-time CPU/GPU thermal states, fan speeds, and frequency throttling detection.
No parameter schema in public metadata yet.
diagnose_antivirus_impactDetects EDR/Antivirus conflicts and exclusion coverage on dev paths.
Detects EDR/Antivirus conflicts and exclusion coverage on dev paths.
No parameter schema in public metadata yet.
monitor_system_healthStatistical health report (CPU load, RAM usage, temperature) with min/max/avg over a configurable time window (up to 10 minutes).
Statistical health report (CPU load, RAM usage, temperature) with min/max/avg over a configurable time window (up to 10 minutes).
No parameter schema in public metadata yet.
check_llm_compatibilityPredicts performance for a specific LLM model via remote API.
Predicts performance for a specific LLM model via remote API.
No parameter schema in public metadata yet.
get_llm_recommendationsRecommends the best local models via remote API.
Recommends the best local models via remote API.
No parameter schema in public metadata yet.
analyze_inference_configDeep-dive into AI runtimes and environment variables.
Deep-dive into AI runtimes and environment variables.
No parameter schema in public metadata yet.
Sponsors
Configuration
REMOTE_API_URLURL of the remote recommendation API
Readme
Yamaru Hardware Probe (MCP)
Expert system hardware probe and performance diagnostic engine for AI, Gaming, and High-Performance workflows. This is a Model Context Protocol (MCP) server that provides deep system insights beyond simple specifications.
Key Features
Details
- Repository
- github.com/yamaru-eu/hardware-probe
- Category
- AI & LLM Tools
- Package
@yamaru-eu/hardware-probe- Transport
- STDIO
- Registry
- MCP registry, active