
SammaPix — Image & PDF tools for AI agents
io.github.samma1997Published by GitHub account samma1997v1.0.0Updated Oct 24, 2026
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Overview
Remote MCP server for image and PDF processing: compress, convert, resize, crop, watermark, inspect metadata, and chain operations in one call.
- What you can do
- Compress, convert (WebP, HEIC), resize, crop, rotate, flip, adjust, blur, tint, add borders or watermarks, and read or strip metadata
- Compress, merge, split and rotate PDFs, convert images to PDF, and extract PDF pages as images
- Generate AI filenames, alt text, photo sorting and OCR text from images
- Chain several image operations in a single pipeline call to cut round-trips
- When to use it
- Useful when an assistant needs to prepare, shrink or convert images and PDFs for the web, batch-process photos, or produce alt text and filenames without a local toolchain.
- Requirements
- Remote Streamable HTTP endpoint at sammapix.com; OAuth 2.1 sign-in is required (a REST key can be generated instead). No local install or environment variables.
Installation
In SourceWeft
- Open SammaPix — Image & PDF tools for AI agents in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.samma1997%2Fsammapix/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"sammapix-image-pdf-tools-for-ai-agents": {
"type": "http",
"url": "https://www.sammapix.com/api/mcp"
}
}
}README
SammaPix
35 free browser-based image tools — compress, convert, rename with AI, and more.
[MIT License] [Next.js] [TypeScript] [Live Site] [Build]
SammaPix is a free, open-source image optimization platform that runs entirely in the browser. No uploads. No account required. No watermarks. Your images never leave your device.
Built for content creators, developers, and anyone who works with images at scale.
[SammaPix — AI Photo Workflow]
Key features:
- 100% client-side processing — images stay on your machine
- 35 tools across four categories (optimize, AI, creative, organize)
- AI-powered rename, alt text generation, and photo sorting via Google Gemini
- Batch processing with ZIP download
- HEIC, WebP, PDF, and video format support
- Dark mode, fully responsive
- Pro plan ($9/month) for unlimited AI credits and larger batches
For AI agents (MCP server)
SammaPix is also a remote MCP server so AI agents (Claude, Cursor, and any MCP-compatible client) can run real image & PDF processing directly — no local install.
- Endpoint:
https://www.sammapix.com/api/mcp(Streamable HTTP) - Auth: OAuth 2.1 — no API key to paste. Or generate a key for REST.
- 20+ tools: compress, convert, resize, crop, rotate, flip, adjust, grayscale, blur, tint, negate, border, round, watermark, metadata · PDF compress/merge/split/rotate, image-to-PDF, PDF info
- Pipeline: chain multiple image ops in one call — fewer round-trips, far fewer tokens for the agent
- Zero-retention: files processed in memory and discarded. Pay-per-use, 25 free ops/day.
Add it to your agent:
Full docs, benefits, and REST examples: sammapix.com/for-ai-agents
Tools
Optimize
AI-Powered
Creative
Organize
Tech Stack
Dashboard
[SammaPix Dashboard]AI Organize
[AI Organize Tool]Quick Start
Open http://localhost:3000.
Most tools work without any API keys — only AI features require a GEMINI_API_KEY.
Required environment variables
Privacy
All image processing tools run entirely in your browser using the Canvas API, WebAssembly, and client-side JavaScript libraries. Your images are never uploaded to any server.
For AI tools (AI Rename, AI Alt Text, AI Organize), a small thumbnail is sent to Google Gemini for analysis. Full-resolution originals never leave your device and are never stored anywhere.
Contributing
Contributions are welcome. Please open an issue before submitting a pull request for significant changes.
- Fork the repo
- Create a feature branch (
git checkout -b feature/your-feature) - Commit your changes
- Open a pull request
For bug reports and feature requests, use GitHub Issues.
License
MIT — see LICENSE for details.
Built by Luca Sammarco · Live at sammapix.com
Source: README.md at commit ef30f3d
Tools
0Version history
1- v1.0.0LatestSep 20, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts