autoclicker-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@autoclicker-mcpstart auto-clicking at the current mouse position for 10 seconds"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
autoclicker-mcp

A Tkinter auto-clicker GUI and an MCP server that exposes the same functionality as AI-callable tools.
The GUI app clicks the left mouse button either for a fixed duration or continuously.
The MCP server lets Claude (or any MCP client) control the clicker, query the cursor position, and locate UI elements by image or OCR text.
Component | Windows | macOS | Linux |
MCP server ( | ✅ | ✅ | ✅ |
GUI ( | ✅ | - | - |
macOS / Linux note: the MCP server uses
pyautoguifor mouse control on non-Windows platforms, sopyautoguiandpilloware required there (see install steps below).
Quick start
# Install core dependency
pip install mcp
# macOS / Linux - also required for mouse control
pip install pyautogui pillow
# Run the GUI (Windows only)
py autoclicker_gui.py
# Run the MCP server (Windows / macOS / Linux)
python mcp_server.pyRelated MCP server: openowl
MCP server
What it exposes
Tool | Description |
| Start clicking (cursor / fixed / image / text mode) |
| Stop clicking |
| JSON status: |
| JSON cursor coords: |
| Single click at an absolute screen position |
| Template-match an image → |
| OCR text search → |
Register with VS Code / Claude Desktop
Add to your MCP client config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"autoclicker": {
"command": "python",
"args": ["a:/Tools/Automator/mcp_server.py"]
}
}
}Optional dependencies for image / OCR modes
# Image matching
py -m pip install pyautogui pillow
# Confidence-based matching (< 1.0)
py -m pip install opencv-python
# OCR text search
py -m pip install pytesseract pyautogui pillow
winget install --id UB-Mannheim.TesseractOCR -eGUI - how to use (Windows only)
The Tkinter GUI uses Win32 global hotkeys and is Windows-only. The MCP server works everywhere.
Choose mode: Timed or Continuous.
Set Clicks per second (max 200).
Pick Click target:
Current cursor - click wherever the mouse is.
Fixed position - click a saved X/Y coordinate.
Find image on screen - locate a UI element by screenshot crop.
Find text on screen (OCR) - locate text like "Start download".
If Timed, set Duration in seconds.
Set Start delay (time to switch to another window).
Press Start.
Hotkeys
Key | Action |
F6 | Start (global) |
F7 | Stop (global) |
Esc | Emergency stop (global) |
These work even when the app is not focused.
Floating controls
Enable Show floating controls to open a small always-on-top Start/Stop panel in the corner of your screen.
Tests
py -m pytest tests/ -vAll 44 tests run without a display, Tesseract, or pyautogui installed.
Notes
Windows only (uses Win32 mouse events).
Click rate is capped at 200 CPS for stability.
Optional Always-on-top toggle keeps the GUI visible over other windows.
This server cannot be deployed
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceGUI automation MCP server that enables AI agents to see and control the Windows desktop using a local Vision LLM (Ollama), supporting screenshot analysis, mouse/keyboard actions, and autonomous task execution.4MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that gives any AI assistant eyes and hands on your desktop — screenshots, clicking, typing, OCR, window management, accessibility-tree queries, workflow recording.5Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server providing AI-friendly computer-use primitives (capture, detect, click) to let LLM agents drive desktop GUI applications on Windows, macOS, and Linux.1MIT
- FlicenseNot gradedqualityCmaintenanceWindows desktop automation MCP server enabling screenshot capture, precise visual locating of UI elements via vision models, and automated mouse clicking.1-