MCP-native AI drawing engine — lets your AI assistant create, edit, and export images
Project description
OmniDraw
The drawing engine built for AI. OmniDraw lets your AI assistant create, edit, and export images — right from the chat.
Install
pip install omnidraw
Supported platforms: Windows (x64), macOS (Apple Silicon), Linux (x64).
Quick start
- Install OmniDraw:
pip install omnidraw
- Add to your MCP client config (Cursor, Claude Desktop, etc.):
{
"mcpServers": {
"omnidraw": {
"command": "omnidraw"
}
}
}
- Reload your MCP client — done! Ask your AI to draw something.
What it does
OmniDraw is an MCP (Model Context Protocol) server that gives AI assistants a full drawing toolkit:
- Shapes & text — rectangles, ellipses, lines, arrows, polygons, text boxes
- Brush engine — strokes, fills, erasing, scatter, smudge, wet brush mixing
- Effects — gradients, shadows, blur, clipping masks, ink diffusion, paper grain
- Layers — create, select, set opacity, toggle visibility
- Projects — save/load
.omnidrawproject files with full undo history - Assets — import images once, reuse across compositions (Pro)
- Export — PNG, JPEG, WebP with optional supersampling (Pro)
Free vs Pro
The free tier covers the core drawing workflow. Upgrade to Pro for:
- Unlimited compositions (free: 2)
- Reusable image assets
- Project save/open
- High-resolution supersampling export
Links
- Website: omnidraw.vercel.app
- Pricing: omnidraw.vercel.app/pricing
- Install guide: omnidraw.vercel.app/docs/install
- Examples: omnidraw.vercel.app/examples
- Source: github.com/timtiger/omnidraw
How it works
This Python package is a thin launcher that bundles a prebuilt Rust binary. When you run omnidraw, it starts the Rust MCP server which communicates with your AI client over stdio.
Diagnostics
omnidraw --print-binary-path
omnidraw --launcher-diagnostics
Environment variables
| Variable | Description |
|---|---|
OMNIDRAW_BIN |
Override the bundled binary path at runtime |
OMNIDRAW_LICENSE_KEY |
Pro license key (from omnidraw.vercel.app/pricing) |
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file omnidraw-0.1.0.tar.gz.
File metadata
- Download URL: omnidraw-0.1.0.tar.gz
- Upload date:
- Size: 4.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5684388b1edcfa80dd4d6eaf86bca47e0f5b0566bdd157b1df7010da26132587
|
|
| MD5 |
35cb28d6e025a8007661615796c4846f
|
|
| BLAKE2b-256 |
ccf01de57cec6c786d5a7218aff3ca8e1305fa93c02a2efab31826cf94a8f9f5
|
File details
Details for the file omnidraw-0.1.0-py3-none-win_amd64.whl.
File metadata
- Download URL: omnidraw-0.1.0-py3-none-win_amd64.whl
- Upload date:
- Size: 4.4 MB
- Tags: Python 3, Windows x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
27ebd66fb8d1953e0e7419079c9ddd9d5fbd1c2becbd02c5312dee7f98366297
|
|
| MD5 |
5dea0157cedf5294c800250b30168ed7
|
|
| BLAKE2b-256 |
a0a1a274a731febc4caac9cfb4a4e18f51882b25f5aead25ace74a275fa54b3a
|
File details
Details for the file omnidraw-0.1.0-py3-none-manylinux_2_17_x86_64.whl.
File metadata
- Download URL: omnidraw-0.1.0-py3-none-manylinux_2_17_x86_64.whl
- Upload date:
- Size: 4.9 MB
- Tags: Python 3, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f1eedafea97e4a5ae494c854f9fd58aa1b3182579bc52ec3aaac4fbba93545a8
|
|
| MD5 |
1093f711247be75a3f8033fe88a6b221
|
|
| BLAKE2b-256 |
efa763e27978a03ab523637cbebdf0b2ba6a59d3375a45bd12fbe832b2e83f4b
|
File details
Details for the file omnidraw-0.1.0-py3-none-macosx_11_0_arm64.whl.
File metadata
- Download URL: omnidraw-0.1.0-py3-none-macosx_11_0_arm64.whl
- Upload date:
- Size: 4.6 MB
- Tags: Python 3, macOS 11.0+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
616c881eaa711459ae8c89a077dc54ee8eb99bfb09877f4c8acbe476b0a944f5
|
|
| MD5 |
4a5aca6bb6b5c554e486eb6d1d226ea2
|
|
| BLAKE2b-256 |
2fe57725436982fc404396af3ba168737dff2b11d5710f6a74ebe7e956b354fd
|