Paint MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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.txtRelated MCP server: aseprite-live-mcp
Usage
python server.pyThis 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 dimensions, current color, brush size, and mode |
| Set drawing color (RGB 0-255) |
| Set brush size (1-50 px) |
| Set brush shape: round, flat, filbert, fan, or palette_knife |
| Draw a single dot |
| Draw a line between two points |
| Draw a rectangle (blocked in oil paint mode) |
| Draw an ellipse (blocked in oil paint mode) |
| Draw a freehand path through coordinate pairs |
| Execute many strokes in one call with per-stroke color/size/shape overrides |
| Smudge/blend existing colors along a path |
| Bucket fill an area (blocked in oil paint mode) |
| Clear to white |
| Undo last operation |
| Read pixel data from a region |
| Save canvas to a temp PNG and return the path for visual inspection |
| Save canvas to a PNG file |
Oil Paint Mode
Tool | Description |
| Toggle oil paint simulation on/off |
| 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.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
Connect AI agents to Flato's editable canvas runtime through a hosted MCP server.
Generate AI images and videos from any compatible MCP client.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Related MCP Servers
- FlicenseAqualityDmaintenanceAn MCP server that enables AI coding agents to create pixel art programmatically by providing canvas manipulation tools and PNG export.1031 npm9-
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets AI agents draw in a live Aseprite editor or headless mode, featuring one-action Unity sprite-sheet export, art-QA sweeps, and game-dev tools.93 PyPI10MIT
- AlicenseAqualityCmaintenanceGives AI agents a real paint canvas over MCP — layers, anti-aliased shapes, paths, brushes, fills, gradients, filters, transforms, undo/redo, and PNG/JPG/BMP/SVG import-export — with every drawing call returning the picture so the model can inspect and correct its own work. Ships one tool per operation plus a batch tool, preview, inspect, and an optional localhost live view.25MIT
- AlicenseNot gradedqualityBmaintenanceEnables LLM-driven painting agents to control Krita through MCP tools, iteratively reconstructing a target image by observing canvas snapshots, diff heatmaps, and session state. It exposes observation, drawing, brush, color, layer, selection, vector, filter, document I/O, and session tools for closed-loop artwork generation.1MIT



