pixelforge
Professional image editing toolkit built for AI agents. CLI, Python API and MCP server. No GUI, no vendor lock-in.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 20 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Alfredo-ctrl/pixelforge with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Alfredo-ctrl/pixelforge'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/alfredo-ctrl--pixelforge)HTML
<a href="/listings/alfredo-ctrl--pixelforge"><img src="/api/listings/alfredo-ctrl--pixelforge/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
pip install pixelforge
Needs Python 3.10+. Background removal is optional:
pip install pixelforge[bg]
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 80 lines
- # pixelforge
- Image editing for AI agents. No GUI, no account, no vendor lock-in: a CLI, a Python API and an MCP server that any agent can drive — Muse, Antigravity, Codex, Claude Code, or a local model.
- ## Install
- ```sh
- pip install pixelforge
- ```
- Needs Python 3.10+. Background removal is optional:
- ```sh
- pip install pixelforge[bg]
- ```
- ## Use it from the terminal
- ```sh
- # what can it do?
- pixelforge ops
- # describe a file
- pixelforge describe photo.jpg
- # edit it: warmer, a bit brighter, gentle vignette
- pixelforge edit -i photo.jpg -o photo-edit.jpg --ops '[
- {"op": "temperature", "value": 18},
- {"op": "exposure", "ev": 0.3},
- {"op": "vignette", "strength": 25}
- ]'
- ```
- Output is JSON, so it is easy to parse:
- ```json
- {"output": "photo-edit.jpg", "format": "JPEG", "size": [4000, 3000], "ops_applied": ["temperature", "exposure", "vignette"]}
- ```
- ## How an agent uses it
- You translate the user's words into ops. `pixelforge ops` lists every operation with its parameters and valid ranges, so there is nothing to guess. Examples:
- - "make it warmer and brighter" -> temperature +15, exposure +0.3
- - "punchy, high contrast black and white" -> grayscale, contrast 1.3, clarity 40
- - "soften the whole frame" -> blur 3
- If the user asks for something that is not an op yet, add it — see CONTRIBUTING.md. That is the whole point: the tool grows with what people ask for.
- ## Use it from Python
- ```python
- from pixelforge import load_image, save_image, apply_ops
- img = load_image("photo.jpg")
- out, applied = apply_ops(img, [{"op": "saturation", "factor": 1.2}])
- save_image(out, "photo-edit.jpg")
- ```
- ## MCP server
- Any MCP client can use pixelforge as tools:
- ```sh
- pixelforge mcp
- ```
- It speaks MCP over stdio and exposes `edit_image`, `describe_image` and `list_operations`. Example client config:
- ```json
- {
- "mcpServers": {
- "pixelforge": {"command": "pixelforge", "args": ["mcp"]}
- }
- }
- ```
- ## License
- MIT
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.