{
  "markdown": "# Yamaru Hardware Probe (MCP)\n\n[![NPM Version](https://img.shields.io/npm/v/@yamaru-eu/hardware-probe?color=blue&logo=npm)](https://www.npmjs.com/package/@yamaru-eu/hardware-probe)\n[![NPM Downloads](https://img.shields.io/npm/dw/@yamaru-eu/hardware-probe?logo=npm)](https://www.npmjs.com/package/@yamaru-eu/hardware-probe)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-io.github.yamaru--eu%2Fhardware--probe-blueviolet?logo=planetscale)](https://modelcontextprotocol.io/)\n[![Awesome MCP](https://awesome.re/badge.svg)](https://github.com/modelcontextprotocol/servers)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)\n[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n\nExpert 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.\n\n## Key Features\n\n- 🔍 **Deep Hardware Inventory**: Comprehensive analysis of CPU, RAM, GPU (VRAM/Bandwidth), Storage, and OS topology.\n- ⚡ **Real-time Performance Monitoring**: Live tracking of system load and identification of resource-hogging processes.\n- 🧊 **Thermal & Power Diagnostics**: Detects thermal throttling and frequency clipping to resolve unexpected slowness.\n- 🤖 **AI/LLM Optimization**: Specialized tools for predicting LLM performance, calculating quantization fit, and optimizing runtimes (Ollama, CUDA, Metal).\n- 🛡️ **Privacy-First**: Automatic anonymization of unique hardware identifiers before any remote transmission.\n\n## Installation\n\n### For Gemini CLI Users\n```bash\ngemini extension install @yamaru-eu/hardware-probe\n```\n\n### For Manual MCP Setup\nAdd this to your MCP settings file (e.g., `npx-config.json` or `claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"yamaru-probe\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@yamaru-eu/hardware-probe\"]\n    }\n  }\n}\n```\n\n## Available Tools\n\n- `analyze_local_system`: Full hardware inventory.\n- `analyze_performance`: Real-time performance metrics and top processes.\n- `analyze_ram_pressure`: Detailed memory pressure and RSS analysis for deep RAM troubleshooting.\n- `check_storage_health`: Disk SMART health, firmware, and I/O bottleneck analysis.\n- `thermal_profile`: Real-time CPU/GPU thermal states, fan speeds, and frequency throttling detection.\n- `diagnose_antivirus_impact`: Detects EDR/Antivirus conflicts and exclusion coverage on dev paths.\n- `monitor_system_health`: Statistical health report (CPU load, RAM usage, temperature) with min/max/avg over a configurable time window (up to 10 minutes).\n- `check_llm_compatibility` **(BETA)**: Predicts performance for a specific LLM model via remote API.\n- `get_llm_recommendations` **(BETA)**: Recommends the best local models via remote API.\n- `analyze_inference_config`: Deep-dive into AI runtimes and environment variables.\n\n## Skills Integration\nWhen used with Gemini CLI, this extension provides the following expert skills:\n- `hardware-performance-expert`: Global protocol for system health and troubleshooting.\n- `local-inference-optimizer`: Specialized logic for fine-tuning local LLM runs.\n\n## Development\n\n```bash\nnpm install        # Install dependencies\nnpm run build      # Compile TypeScript → dist/\nnpm run test       # Run test suite\nnpm run inspector  # Test tools in the MCP Inspector\n```\n\n## License\nApache 2.0 - Part of the Yamaru Project.\n",
  "bytes": 3554,
  "sha": "3511678a28905d22ae6acaf7acda881caf4bb90bf7f4fc5b70c344951c18660a",
  "repo_slug": "yamaru-eu/hardware-probe",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_yamaru_eu_hardware_probe_d77b8350/readme"
}