一个隔离的、带 GPU 分区的本地 Windows 11 虚拟机环境，通过 Model Context Protocol (MCP) 连接，专为 AI 编程智能体设计，用于执行自动化 Blender UI 测试、用户故事验证和 Computer-Use 工作流，且不干扰宿主机桌面。
+---------------------------------------------------------------------------------------------+
| Coding Agents (Claude Code / OMP / Codex) |
+---------------------------------------------------------------------------------------------+
│
│ (MCP JSON-RPC via stdio)
▼
+─────────────────────────────────────────────────────────────────────────────────────────────+
| Host Layer: `blender-cu-vm-mcp` Server |
| - MCP Tool Handler (Computer Use, Analytical Inspection, Blender Telemetry, File Staging) |
| - VM Lifecycle Manager (Hyper-V Socket / PowerShell WMI / Sub-2s Snapshot Reset) |
+─────────────────────────────────────────────────────────────────────────────────────────────+
│
┌───────────────────────┴───────────────────────┐
│ Hyper-V Socket (HV-SOCK) / Internal VMSwitch │
▼ ▼
+───────────────────────────────────────────────+ +─────────────────────────────────────────+
| Windows 11 Guest VM (Hyper-V) | | Secondary (Fast CI): WSL2 Container |
| - NVIDIA GPU-PV (RTX 4080 Super vGPU: 8GB) | | - Mesa / Direct3D 12 GPU Accel |
| - Virtual Display Driver (1080p Fixed 60Hz) | | - Virtual X11 Display (Xvfb/Weston) |
| - Guest Agent Daemon (FastAPI / gRPC) | | - Guest Agent Daemon (Linux) |
| - In-Process Blender Telemetry Bridge (bpy) | | - Blender bpy IPC Bridge |
+───────────────────────────────────────────────+ +─────────────────────────────────────────+Related MCP server: WindowsPC-MCP
零宿主机干扰： 合成的鼠标移动、拖拽、点击和键盘输入仅在客户机操作系统内部执行，真实光标和窗口焦点完全不受影响。
硬件加速 GPU 渲染： NVIDIA GPU-PV 为客户虚拟机提供近乎原生的宿主机 RTX 4080 Super 访问能力（DirectX 12、Vulkan、OpenGL 和 CUDA/OptiX）。
确定性 1080p 显示： 开源虚拟显示驱动（IddSampleDriver）将虚拟屏幕锁定为 1920×1080 @ 60Hz、100%（96 DPI）缩放，防止坐标漂移和显示器休眠。
混合多模态反馈： 智能体可接收：
视觉： 带可选坐标网格的帧缓冲截图。
分析： Windows UI Automation 树、边界框和窗口响应性。
深度遥测： Blender bpy 状态、活动修改器、节点树连接以及实时 stdout/stderr 日志。
两秒内状态回滚： 快速的 Hyper-V 快照恢复功能可在破坏性或实验性运行后，将虚拟机重置为干净的黄金基线状态。
blender-cu-vm/
├── host/ # Host MCP Server & Hyper-V Controller
│ ├── mcp_server.py # Stdio JSON-RPC MCP server with 14 tools
│ ├── hv_transport.py # Hyper-V Socket (AF_HYPERV) & HTTP transport
│ ├── vm_controller.py # PowerShell WMI lifecycle & snapshot manager
│ └── asset_sync.py # Bi-directional file and addon staging
├── guest/ # Guest Agent Daemon (runs inside VM)
│ ├── guest_daemon.py # FastAPI HTTP/HV-SOCK unified server
│ ├── screen_capture.py # DXGI Desktop Duplication & visual diffs
│ ├── input_controller.py # Win32 SendInput (clicks, drags, typing)
│ ├── ui_automation.py # Windows UI Automation tree inspector
│ └── video_recorder.py # Hardware-accelerated NVENC MP4 recorder
├── blender/ # Blender Embedded Runtime Bridge
│ ├── cu_telemetry_bridge.py # Non-blocking TCP telemetry server
│ ├── crash_interceptor.py # C-level stdout/stderr stream tee
│ └── state_inspector.py # Declarative scene invariant checker
├── scripts/ # Automated Setup & Provisioning
│ ├── setup_vm_gpupv.ps1 # Automated Hyper-V Gen2 VM creator
│ ├── stage_gpupv_drivers.ps1 # NVIDIA GPU-PV driver packaging & injection
│ ├── setup_virtual_display.ps1 # Virtual display & autologon configuration
│ └── manage_golden_snapshot.ps1 # Instant snapshot creation & rollback
├── tests/ # Verification & E2E Test Suite
│ ├── test_blender_user_story.py # 12-stage automated test suite
│ └── verify_isolation.py # Zero host disturbance verification
├── mcp-config.json # Registration snippet for Claude Code / OMP
└── README.mdcd C:\tmp\blender-cu-vm\scripts
.\setup_vm_gpupv.ps1 -VMName "Blender-CU-VM" -MemoryBytes 8GB -ProcessorCount 8.\stage_gpupv_drivers.ps1 -VMName "Blender-CU-VM" -Mode "Stage"在客户机虚拟机内（以管理员身份运行 PowerShell）：
# 1. Install GPU-PV drivers from staged directory
C:\Temp\NvidiaDrivers\install_gpupv_guest.bat
# 2. Configure Virtual Display & Auto-Logon
.\setup_virtual_display.ps1 -TargetWidth 1920 -TargetHeight 1080
# 3. Start Guest Daemon on boot
python C:\blender-cu-vm\guest\guest_daemon.py.\manage_golden_snapshot.ps1 -VMName "Blender-CU-VM" -SnapshotName "golden_base" -Action "Create"将以下配置添加到你的 ~/.claude.json 或 ~/.omp/agent/config.yml 中：
{
"mcpServers": {
"blender-cu-vm": {
"command": "python",
"args": [
"C:\\tmp\\blender-cu-vm\\host\\mcp_server.py"
],
"env": {
"BLENDER_VM_NAME": "Blender-CU-VM",
"BLENDER_GUEST_URL": "http://192.168.122.100:8000"
}
}
}
}要验证所有子系统并运行模拟的 Blender 用户故事：
python blender-cu-vm/tests/test_blender_user_story.py
python blender-cu-vm/tests/verify_isolation.pyThis server cannot be deployed
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
Blender and GLB/FBX/USD/STL rendered on cloud GPUs for AI agents: product shots, turntables, MP4
Secure AI access to Windows, macOS, Linux computers and a hosted Cloud Browser.
Persistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.
