PluginBench
MCP Server
Active
MIT

SammaPix — Image & PDF tools for AI agents MCP Server

io.github.samma1997/sammapix

35 free browser-based image & PDF tools for AI agents: compress, convert, resize, AI rename, and more.

What is the SammaPix — Image & PDF tools for AI agents MCP server?

SammaPix is a remote MCP server providing 20+ image and PDF processing tools for AI agents like Claude and Cursor. It offers compress, convert, resize, crop, rotate, PDF operations, and AI-powered features like rename and alt-text generation—all running client-side with zero data retention and pay-per-use pricing (25 free ops/day).

SammaPix exposes a suite of image optimization, AI-powered, creative, and organizational tools via MCP. AI agents can chain multiple image operations in a single call, reducing round-trips and token usage. All processing is client-side; files are discarded after use. Authentication via OAuth 2.1 or API key; Pro plan ($9/month) unlocks unlimited AI credits.

How to install SammaPix — Image & PDF tools for AI agents

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "sammapix": {
      "url": "https://www.sammapix.com/api/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Compress — Reduce image file size without visible quality loss
  • WebP Converter — Convert JPG/PNG to WebP for faster web delivery
  • HEIC Converter — Convert iPhone HEIC photos to JPG or PNG
  • Batch Resize — Resize multiple images by pixel dimensions or percentage
  • Crop & Ratio — Crop to standard aspect ratios or custom dimensions
  • PDF to Image — Extract pages from PDF as high-quality images
  • AI Organize — Drop 100+ photos — AI sorts them into named folders
  • AI Rename — Generate descriptive, SEO-friendly filenames automatically
  • AI Alt Text — Generate accessibility alt text for any image
  • AI Photo Sort — Sort photos by subject, scene, or custom criteria
  • Web Optimize — AI-assisted optimization for web performance
  • Transcribe — Extract text from images (OCR)
  • Film Filters — Apply 14 analog film presets (Kodak, Fuji, Polaroid, etc.)
  • Watermark — Add text or image watermarks with custom positioning
  • EXIF Viewer — Inspect full metadata — GPS, camera, exposure, timestamps
  • EXIF Remover — Strip GPS and privacy data before sharing
  • Find Duplicates — Detect duplicate images by visual similarity
  • Batch Rename — Rename files in bulk with custom patterns and sequences
  • Cull — Quickly review and select keepers from a shoot
  • Sort by Location — Group photos by GPS coordinates on an interactive map

Use cases

  • Batch compress and convert images to WebP for web optimization without leaving your device
  • Generate SEO-friendly filenames and alt text for 100+ photos using AI in a single operation
  • Extract text from images (OCR) and organize photos by location or AI-detected subject matter
  • Strip EXIF metadata and GPS data from photos before sharing for privacy
  • Chain multiple image operations (resize, crop, watermark, filter) in one MCP call to reduce token usage

SammaPix — Image & PDF tools for AI agents MCP server FAQ

What is SammaPix?

SammaPix is a free, open-source image and PDF processing platform available as both a web app and remote MCP server. The MCP server lets AI agents like Claude and Cursor run 20+ image/PDF tools directly without local installation.

Is SammaPix free?

Yes. The web app and MCP server are free with 25 free operations per day. A Pro plan ($9/month) offers unlimited AI credits and larger batch sizes.

How do I add SammaPix to Claude or Cursor?

Add the remote MCP server URL to your client config: {"mcpServers": {"sammapix": {"url": "https://www.sammapix.com/api/mcp"}}}. Authentication uses OAuth 2.1 or an API key.

Does SammaPix upload my images?

No. All image processing runs client-side in your browser. For AI features, only a small thumbnail is sent to Google Gemini; full-resolution originals never leave your device and are never stored.

What authentication does the MCP server require?

OAuth 2.1 (no API key to paste) or you can generate an API key for REST calls. Both methods are supported.

Can I chain multiple image operations in one call?

Yes. The MCP server supports pipelines that chain multiple image operations (compress, resize, crop, watermark, etc.) in a single call, reducing round-trips and token usage for AI agents.

README (reference)

Source of truth, from the repository.

<h1 align="center">SammaPix</h1> <p align="center"><strong>35 free browser-based image tools — compress, convert, rename with AI, and more.</strong></p> <p align="center"> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-black.svg" alt="MIT License"></a> <a href="https://nextjs.org"><img src="https://img.shields.io/badge/Next.js-15-black?logo=next.js" alt="Next.js"></a> <a href="https://typescriptlang.org"><img src="https://img.shields.io/badge/TypeScript-5-blue?logo=typescript" alt="TypeScript"></a> <a href="https://www.sammapix.com"><img src="https://img.shields.io/badge/Live-sammapix.com-6366f1" alt="Live Site"></a> <a href="https://github.com/samma1997/sammapix/actions/workflows/ci.yml"><img src="https://github.com/samma1997/sammapix/actions/workflows/ci.yml/badge.svg" alt="Build"></a> </p>

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.

<p align="center"> <img src="public/screenshots/hero-dark.png" alt="SammaPix — AI Photo Workflow" width="100%"> </p>

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:

{
  "mcpServers": {
    "sammapix": { "url": "https://www.sammapix.com/api/mcp" }
  }
}

Full docs, benefits, and REST examples: sammapix.com/for-ai-agents


Tools

Optimize

ToolDescription
CompressReduce file size without visible quality loss
WebP ConverterConvert JPG/PNG to WebP for faster web delivery
HEIC ConverterConvert iPhone HEIC photos to JPG or PNG
Batch ResizeResize multiple images by pixel dimensions or percentage
Crop & RatioCrop to standard aspect ratios or custom dimensions
PDF to ImageExtract pages from PDF as high-quality images

AI-Powered

ToolDescription
AI OrganizeDrop 100+ photos — AI sorts them into named folders
AI RenameGenerate descriptive, SEO-friendly filenames automatically
AI Alt TextGenerate accessibility alt text for any image
AI Photo SortSort photos by subject, scene, or custom criteria
Web OptimizeAI-assisted optimization for web performance
TranscribeExtract text from images (OCR)

Creative

ToolDescription
Film FiltersApply 14 analog film presets (Kodak, Fuji, Polaroid, etc.)
WatermarkAdd text or image watermarks with custom positioning

Organize

ToolDescription
EXIF ViewerInspect full metadata — GPS, camera, exposure, timestamps
EXIF RemoverStrip GPS and privacy data before sharing
Find DuplicatesDetect duplicate images by visual similarity
Batch RenameRename files in bulk with custom patterns and sequences
CullQuickly review and select keepers from a shoot
Sort by LocationGroup photos by GPS coordinates on an interactive map
Photo MapVisualize where your photos were taken

Tech Stack

LayerTechnology
FrameworkNext.js 15 (App Router)
LanguageTypeScript 5
StylingTailwind CSS
StateZustand + Immer
AuthNextAuth.js v4 (Google, GitHub, Magic Link)
DatabaseNeon (PostgreSQL) via Drizzle ORM
AIGoogle Gemini 1.5 Flash
PaymentsStripe
EmailResend
Compressionbrowser-image-compression
HEICheic-convert / heic2any
Batch downloadJSZip + file-saver
TestingPlaywright (E2E)

<p align="center"> <img src="public/screenshots/tools-dark.png" alt="27 Free Tools" width="100%"> </p> <details> <summary><strong>Dashboard</strong></summary> <img src="public/screenshots/dashboard.png" alt="SammaPix Dashboard" width="100%"> </details> <details> <summary><strong>AI Organize</strong></summary> <img src="public/screenshots/ai-organize.png" alt="AI Organize Tool" width="100%"> </details>

Quick Start

git clone https://github.com/samma1997/sammapix.git
cd sammapix
npm install
cp .env.local.example .env.local   # fill in your keys
npm run dev

Open http://localhost:3000.

Most tools work without any API keys — only AI features require a GEMINI_API_KEY.

Required environment variables

# Auth
NEXTAUTH_SECRET=
GOOGLE_CLIENT_ID=
GOOGLE_CLIENT_SECRET=

# Database
DATABASE_URL=          # Neon PostgreSQL connection string

# AI (required for AI tools only)
GEMINI_API_KEY=

# Payments (required for Pro plan only)
STRIPE_SECRET_KEY=
STRIPE_WEBHOOK_SECRET=
NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=
STRIPE_PRO_PRICE_ID=

NEXT_PUBLIC_APP_URL=http://localhost:3000

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.

  1. Fork the repo
  2. Create a feature branch (git checkout -b feature/your-feature)
  3. Commit your changes
  4. 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

Related MCP servers

ALAlgernon MCP logo

Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.

0
Python
View repository →
ARArkHive MCP logo

Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.

1
Python
View repository →

Give your AI agents rules, memory, and receipts. Governed multi-agent orchestration for MCP.

View repository →

Scores your prompts against your real codebase — context-aware prompt intelligence

1
TypeScript
MIT
View repository →

Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms for AI assistants.

19
TypeScript
MIT
View repository →

Manage restaurant employee scheduling, time-off, tips, and payroll via ShiftZap.

View repository →