MCP Server for Microsoft Paint
Description
# MCP Server for Microsoft Paint A JSON-RPC 2.0 compatible server for controlling Microsoft Paint through the Microsoft Commandline Protocol (MCP). ## Features - Launch and connect to Microsoft Paint - Draw lines, shapes, and pixels - Set colors and tool properties - Control the…
About
# MCP Server for Microsoft Paint A JSON-RPC 2.0 compatible server for controlling Microsoft Paint through the Microsoft Commandline Protocol (MCP). ## Features - Launch and connect to Microsoft Paint - Draw lines, shapes, and pixels - Set colors and tool properties - Control the Paint window ## Requirements - Windows…
Details
- Author
- ghuntley
- GitHub stars
- 20
- Downloads
- 349
- Categories
- Other
Jump to
- Launch and connect to Microsoft Paint
- Draw lines, shapes, and pixels
- Set colors and tool properties
- Control the Paint window (e.g., activate, get dimensions)
- Operates over JSON‑RPC 2.0 via stdin/stdout
- Includes a Python test client for demonstration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server for Microsoft PaintCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Build the server with cargo build --release and run it with cargo run --release. The server accepts JSON‑RPC 2.0 requests via stdin and responds via stdout. A Python test client (final_test.py) is provided and can be run with python final_test.py.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server for microsoft paint": {
"mcp-server-microsoft-paint": {
"command": "python",
"args": [
"final_test.py"
]
}
}
}
}McpServers
{
"mcp-server-microsoft-paint": {
"command": "python",
"args": [
"final_test.py"
]
}
}MCP Server for Microsoft Paint
A JSON-RPC 2.0 compatible server for controlling Microsoft Paint through the Microsoft Commandline Protocol (MCP).
Features
- Launch and connect to Microsoft Paint
- Draw lines, shapes, and pixels
- Set colors and tool properties
- Control the Paint window
Requirements
- Windows 10/11 with Microsoft Paint installed
- Rust (for building the server)
- Python (for the test client examples)
Building and Running
To build the server:
cargo build --release
To run the server:
cargo run --release
The server accepts JSON-RPC 2.0 requests via stdin and responds via stdout.
JSON-RPC Methods
initialize
Finds or launches Microsoft Paint.
Request:
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {}
}
connect
Connects to an already running Paint window.
Request:
{
"jsonrpc": "2.0",
"id": 2,
"method": "connect",
"params": {
"client_id": "your-client-id",
"client_name": "Your Client Name"
}
}
draw_line
Draws a line from one point to another.
Request:
{
"jsonrpc": "2.0",
"id": 3,
"method": "draw_line",
"params": {
"start_x": 100,
"start_y": 100,
"end_x": 300,
"end_y": 100,
"color": "#FF0000",
"thickness": 3
}
}
Other Methods
- activate_window - Brings the Paint window to the foreground
- get_canvas_dimensions - Returns the current canvas size
- draw_pixel - Draws a single pixel
- draw_shape - Draws a shape (rectangle, ellipse, etc.)
- select_tool - Selects a drawing tool
- set_color - Sets the current color
- And more...
Example Test Client
A simple test client is provided in final_test.py to demonstrate how to use the server:
python final_test.py
Troubleshooting
If you encounter issues with the server connecting to Paint:
1. Make sure Microsoft Paint is installed and accessible
2. Try manually launching Paint before starting the server
3. Check the server logs for detailed error messages
License
This project is available under the MIT License.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
