NeuroPaint-X
Allows loading fonts from Google Fonts for drawing text, such as specifying a font name like Poppins.
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.
NeuroPaint-X
An MCP server that gives an AI an Ibis-Paint-level image editor — a layered
raster painting canvas it drives with tool calls, renders, looks at, and
iterates on. (Python package name: mcp_paint.)
Stateful documents held in server memory: layers, blend modes, opacity, alpha-lock, undo/redo.
skia-python rendering: anti-aliased brushes (soft/hard/ink/marker/airbrush/ pencil), shapes, linear/radial gradients, flood fill, text, filters (blur / drop-shadow / glow / grayscale / saturate / brightness / contrast / invert / sharpen).
Pulls images and fonts straight from the internet —
place_image(url=…),draw_text(google_font="Poppins")orfont_url=….Token-frugal by design (see below).
Keeping token cost low
Image tokens ≈ width*height / 750. NeuroPaint-X minimises them:
lever | effect |
Mutating tools return one terse text line, never an image | you only pay image tokens when you choose to look |
|
|
| inspect a detail at high zoom without paying for the whole canvas |
| dozens of draw ops in one tool call = one round-trip, one undo step |
| writes a full-res PNG to disk — zero image tokens |
Each render reply also reports approx_image_tokens so the model can self-budget.
Related MCP server: zibel
Run it
python -m venv .venv && . .venv/bin/activate
pip install -e .
# HTTP (for a Claude connector) — default 127.0.0.1:8765
python -m mcp_paint
# or stdio (for local Claude Code / Desktop)
MCP_PAINT_TRANSPORT=stdio python -m mcp_paintEnvironment
var | default | meaning |
|
|
|
|
| HTTP bind |
| (unset) | if set, require |
|
| where |
|
| downloaded images/fonts |
|
| max bytes per fetched asset |
Use as a Claude connector (self-hosted)
Run it on your box, bound to localhost, with a token:
MCP_PAINT_TOKEN=$(openssl rand -hex 24) python -m mcp_paintExpose that port over HTTPS with a tunnel:
cloudflared tunnel --url http://localhost:8765 # quick throwaway URL # or: tailscale funnel 8765 / ngrok http 8765In Claude → Settings → Connectors → Add custom connector:
URL
https://<your-tunnel>/mcpAuthentication: None (the server uses a shared header secret, not OAuth)
Additional request headers → Add header:
X-Paint-Token=<your MCP_PAINT_TOKEN>(Authorization=Bearer <token>also works)
With no
MCP_PAINT_TOKENthe server is open to anyone who has the tunnel URL. Set one.
Local Claude Code
.mcp.json (see .mcp.json.example):
{
"mcpServers": {
"paint": {
"command": "/ABS/PATH/NeuroPaint-X/.venv/bin/python",
"args": ["-m", "mcp_paint"],
"env": { "MCP_PAINT_TRANSPORT": "stdio" }
}
}
}Tool map
new_canvas · list_canvases · canvas_info · delete_canvas
render · export · pick_color · undo · redo
add_layer · select_layer · update_layer · delete_layer · duplicate_layer
· move_layer · merge_down · clear_layer
stroke · draw_rect · draw_ellipse · draw_line · draw_polygon
· draw_gradient · bucket_fill · draw_text · place_image · filter_layer
batch
Coordinates are pixels, origin top-left. Colors: #rgb / #rrggbb /
#rrggbbaa / rgb() / rgba() / CSS names / [r,g,b(,a)].
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
Lets AI assistants draw: logos, posters, illustrations and scenes, as editable SVG and PNG.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
Agent-Native design tool - create and edit visual designs with agent assistance
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA full-featured image processing MCP server for AI assistants, exposing ~55 tools across 11 categories for editing, layers, conversion, AI segmentation/cleanup/generation, design analysis, and screenshot-to-code.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create and edit vector drawing documents over MCP, with tools to draw shapes, read document outlines, and render PNG previews while humans work in the same Illustrator-style canvas.Apache 2.0
- 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 gradedqualityCmaintenanceLets MCP clients such as Claude, Cursor or VS Code drive a locally installed image editor from plain-language requests, opening files, building and managing layers, making selections, applying adjustments and filters, and exporting the finished result. It exposes 65 tools covering layers, documents, adjustments, selections, filters, undo/redo state and export formats like PNG, PSD and WebP.5MIT