Skip to main content

Windows MCP Daemon — 74-tool AI operating system for Windows. Screen capture, browser automation (CDP), native app control (UIA), file operations, clipboard, process management, and Premiere Pro integration. Patent 10: Cross-Instance AI Coordination Protocol.

Project description

love-wmcp

Windows MCP Daemon — A 74-tool AI operating system for Windows by Love Technologies.

Give any AI agent full control of a Windows desktop: screen capture, browser automation, native app control, file management, and more. Built for Claude but works with any MCP-compatible client.

Patent 10: Cross-Instance AI Coordination Protocol via Universal Task Record Bus

Three Components

Component Command Port Description
Daemon wmcp-daemon 8765 Persistent HTTP service. 74 tools. Screen buffer, window targeting, CDP, UIA.
Remote wmcp-remote 8766 FastMCP/SSE server. 42 tools. Cloudflare Tunnel ready for remote access.
Bridge wmcp stdio CLI tool. Routes to daemon (HTTP) or windows-mcp (stdio) based on tool name.

74 Tools Across 6 Categories

Screen / Window (Frame Buffer)

Continuous background screen capture with ring buffer. Target specific windows or full desktop.

App / Process Management

Launch, focus, close, and enumerate applications.

File / Clipboard

Read, write, append files. Get/set clipboard contents.

Browser Automation (Chrome DevTools Protocol)

Full browser control via CDP on port 9222. No pixel coordinates needed — click by text or selector.

Native UI Automation (UIA / pywinauto)

Control native Windows applications by element name, automation ID, or control type.

Premiere Pro Integration

Remote control Adobe Premiere Pro for video editing workflows.

Install

pip install love-wmcp

# With browser automation (Playwright/CDP)
pip install love-wmcp[browser]

# With native UI automation (pywinauto)
pip install love-wmcp[uia]

# Everything
pip install love-wmcp[all]

Quick Start

# Start the daemon
wmcp-daemon

# Use the CLI bridge
wmcp wmcp_list_windows
wmcp wmcp_launch_app '{"name": "notepad"}'

# Or start the remote server for Cloudflare Tunnel access
wmcp-remote

Remote Access (Cloudflare Tunnel)

wmcp-daemon &
wmcp-remote &
cloudflared tunnel run wmcp

The remote server exposes 42 tools via Streamable HTTP on port 8766. Point a Cloudflare Tunnel at it for secure remote AI-to-machine communication.

Requirements

  • Windows 10/11
  • Python >= 3.10
  • Chrome (for CDP browser tools, started with --remote-debugging-port=9222)

Part of the Love Technologies Ecosystem

  • TaScan — Universal task protocol. tascan.io
  • The Council — Multi-LLM adversarial consensus engine
  • CCSP — Persistent AI identity infrastructure
  • 10 provisional patents filed (265 claims)

License

MIT

Author

Michael Edward Love II — Michael@TaScan.io — Love Technologies

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

love_wmcp-1.0.0.tar.gz (24.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

love_wmcp-1.0.0-py3-none-any.whl (26.4 kB view details)

Uploaded Python 3

File details

Details for the file love_wmcp-1.0.0.tar.gz.

File metadata

  • Download URL: love_wmcp-1.0.0.tar.gz
  • Upload date:
  • Size: 24.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for love_wmcp-1.0.0.tar.gz
Algorithm Hash digest
SHA256 221ee7907a3f47756110c462166b098c1b11ed8acf4957a0aa3b0b3fddc90bba
MD5 d015270bc1b9686462f1651cdfb10e6b
BLAKE2b-256 522c5acce634d515270025391424524006d62b447e30b112fc3a16f9ac8f1f59

See more details on using hashes here.

File details

Details for the file love_wmcp-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: love_wmcp-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 26.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for love_wmcp-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9d3f9291556cfc80dcbe3c84935e0bf063c06b52d7a1b993d44f7bb5458a81a8
MD5 5a7f738d79f75e788b4c13e9cc3f3ef3
BLAKE2b-256 8cf86e44d272eb3a72f2baa9886e00a55f4af203921950ecd17e06e6b1d8ec7b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page