This MCP server provides drawing capabilities for AI assistants, enabling them to create and manipulate visual content through a simple canvas interface. You can use it to create drawings programmatically with features like creating canvases, drawing shapes, and exporting images.
The easiest way to install the drawing MCP server is through Smithery:
npx -y @smithery/cli install @flrngel/mcp-painter --client claude
This command automatically sets up the MCP server for Claude Desktop.
To install the drawing MCP server manually, add the following configuration to your MCP config:
"painter": {
"command": "npx",
"args": ["-y", "github:flrngel/mcp-painter"]
}
First, create a new canvas by specifying its dimensions:
// Create a 500x300 canvas
const canvas = await mcp.painter.createCanvas({
width: 500,
height: 300
});
Once you have a canvas, you can draw shapes on it:
// Draw a filled blue rectangle
await mcp.painter.fillRect({
x: 50, // x-coordinate of top-left corner
y: 75, // y-coordinate of top-left corner
width: 200, // width of rectangle
height: 100, // height of rectangle
color: "#0000FF" // blue color in hex format
});
You can export your drawing as a PNG image:
// Export the canvas as a PNG image
const image = await mcp.painter.exportAsPNG();
To retrieve the raw canvas data as JSON:
// Get the canvas data
const canvasData = await mcp.painter.getCanvasData();
Here's a complete example that creates a simple drawing:
// Create a new canvas
const canvas = await mcp.painter.createCanvas({
width: 600,
height: 400
});
// Draw a blue sky
await mcp.painter.fillRect({
x: 0,
y: 0,
width: 600,
height: 300,
color: "#87CEEB"
});
// Draw green grass
await mcp.painter.fillRect({
x: 0,
y: 300,
width: 600,
height: 100,
color: "#228B22"
});
// Draw a yellow sun
await mcp.painter.fillRect({
x: 500,
y: 50,
width: 50,
height: 50,
color: "#FFD700"
});
// Export the image
const image = await mcp.painter.exportAsPNG();
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.