Paint MCP
Exposes a Pygame-based drawing canvas as an MCP server, allowing LLMs to create digital art using standard shapes and freehand paths. It features a specialized oil paint mode that simulates realistic color mixing, paint depletion, and textured brush strokes.
README
Paint MCP
A drawing canvas exposed as an MCP server. An LLM connects over stdio and paints on a pygame window using tool calls.
Setup
pip install -r requirements.txt
Usage
python server.py
This opens an 800x600 pygame canvas and starts the MCP server on stdio. Connect any MCP-compatible client (e.g. Claude Desktop) to the process.
MCP Tools
| Tool | Description |
|---|---|
get_canvas_info |
Get canvas dimensions, current color, brush size, and mode |
set_color |
Set drawing color (RGB 0-255) |
set_brush_size |
Set brush size (1-50 px) |
set_brush_shape |
Set brush shape: round, flat, filbert, fan, or palette_knife |
draw_point |
Draw a single dot |
draw_line |
Draw a line between two points |
draw_rect |
Draw a rectangle (blocked in oil paint mode) |
draw_ellipse |
Draw an ellipse (blocked in oil paint mode) |
draw_path |
Draw a freehand path through coordinate pairs |
batch_strokes |
Execute many strokes in one call with per-stroke color/size/shape overrides |
blend_path |
Smudge/blend existing colors along a path |
flood_fill |
Bucket fill an area (blocked in oil paint mode) |
clear_canvas |
Clear to white |
undo |
Undo last operation |
get_canvas_pixels |
Read pixel data from a region |
preview_canvas |
Save canvas to a temp PNG and return the path for visual inspection |
save_canvas |
Save canvas to a PNG file |
Oil Paint Mode
| Tool | Description |
|---|---|
set_oil_paint_mode |
Toggle oil paint simulation on/off |
get_oil_painting_guide |
Get a technique guide for realistic oil painting |
When oil paint mode is enabled:
- Color mixing — the brush picks up existing canvas color as it moves, so overlapping strokes blend naturally.
- Paint depletion — strokes start opaque and gradually thin out as the brush runs dry. Each new stroke reloads the brush.
- Soft edges — dabs use concentric rings with cubic falloff for painterly texture.
- Brush shapes — five brush types (round, flat, filbert, fan, palette_knife) create distinct stroke characteristics. Flat for broad washes, filbert for general work, fan for blending, palette knife for bold impasto.
- Shapes disabled — rectangles, ellipses, and flood fill are blocked. Only points, lines, and paths are available.
batch_strokesis the recommended way to paint — send many short strokes per call, each with its own color, brush size, and brush shape.
Examples
Regular mode
| Starry Night | Meme |
|---|---|
![]() |
![]() |
Oil paint mode
| Sunset | Alien Sunset |
|---|---|
![]() |
![]() |
Architecture
server.py— Entry point. Runs the pygame main loop and drains commands from a thread-safe queue.tools.py— MCP tool definitions. Pushes drawing commands onto the queue.canvas.py— Drawing engine. Wraps a pygame surface with draw ops, oil paint simulation, and an undo stack.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.



