image-metadata-embed-and-report
A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators, enabling metadata embedding, reading, validation, and report generation for lifestyle, product, and orbit schemas.
README
Image Metadata Embed and Report
A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators. Features professional XMP display and automatic "_me" suffix for processed images.
✨ Features
✅ Beautiful XMP Formatting: Clean, aligned metadata display without technical prefixes
✅ Smart "_me" Filename Suffix: Instant visual indicator for metadata-enhanced images
✅ 📊 Category-Based Reports: Metadata organized by natural categories with analysis type headers
✅ 🎯 Analysis Type Identification: Clear "LIFESTYLE/PRODUCT/ORBIT" headers in all reports
✅ 5 Core Tools: embed, read, validate, create_xmp, create_metadata_report with improved UX
✅ Stream Processing: Memory-only image processing, no local files
✅ Multi-Schema Support: Lifestyle, Product, and Orbit schemas
✅ Supabase Integration: Seamless cloud storage processing
✅ TypeScript: Full type safety and modern development
✅ Zero Setup: Single build command, immediate productivity
Quick Start
1. Install Dependencies
npm install
2. Set Environment Variables
Copy the example environment file and configure your Supabase credentials:
cp .env.example .env
Edit .env with your Supabase project details:
SUPABASE_URL=https://your-project-id.supabase.co
SUPABASE_ANON_KEY=your_anon_key_here
SUPABASE_BUCKET_NAME=your_storage_bucket_name
Get these values from your Supabase project dashboard at https://supabase.com/dashboard/project/_/settings/api
3. Build and Start
npm run build
npm start
4. Configure Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"image-metadata-embed-and-report": {
"command": "node",
"args": ["/path/to/your/image-metadata-embed-and-report/dist/server.js"],
"env": {
"SUPABASE_URL": "https://your-project-id.supabase.co",
"SUPABASE_ANON_KEY": "your_anon_key_here",
"SUPABASE_BUCKET_NAME": "your_storage_bucket_name"
},
"description": "Image Metadata Embed and Report - XMP metadata with beautiful formatting"
}
}
}
Replace /path/to/your/image-metadata-embed-and-report/ with the actual path where you cloned this repository.
✨ Enhanced Features Overview
Beautiful XMP Display
Transform technical metadata into professional, readable format:
Before:
Lifestyle marketing potential emotional hooks: Comfort, Pleasure, Well-being
Product physical characteristics primary color: Silver/Gray
After:
emotional hooks : Comfort, Pleasure, Well-being
primary color : Silver/Gray
--- Raw JSON ---
{"lifestyle_marketing_potential_emotional_hooks": "Comfort, Pleasure, Well-being", ...}
Smart Filename Suffix
All processed images automatically get "_me" suffix:
# Input → Output
restaurant_scene.png → restaurant_scene_me.jpg
product_photo.tiff → product_photo_me.jpg
folder/image.png → folder/image_me.jpg
Benefits:
- ✅ Instant visual identification of processed images
- ✅ Preserves original file names and organization
- ✅ Automatic format conversion for universal XMP support
Available Tools
1. embed_image_metadata (Enhanced)
Embed XMP metadata with beautiful formatting and smart filename suffix.
{
"source_path": "images/restaurant_scene.png",
"metadata": {
"scene_overview": {
"setting": "Outdoor restaurant patio",
"time_of_day": "Evening"
},
"human_elements": {
"number_of_people": 8,
"social_dynamics": "Friends enjoying dinner"
},
"marketing_potential": {
"emotional_hooks": ["Social connection", "Relaxed dining"]
}
},
"output_path": "processed/restaurant_scene.png",
"schema_type": "lifestyle"
}
Enhanced Output:
- 📁 File:
processed/restaurant_scene_me.jpg(automatic suffix + conversion) - ✨ Beautiful XMP: Clean, aligned field display without technical prefixes
- 🔄 Auto-conversion: PNG/TIFF → JPG for universal compatibility
- 📊 Metrics: Processing time, field count, completeness score
2. read_image_metadata (Enhanced)
Extract and display metadata with beautiful formatting.
{
"image_path": "processed/restaurant_scene_me.jpg",
"format": "formatted",
"include_xmp": true
}
Beautiful Output:
setting : Outdoor restaurant patio
time of day : Evening
number of people : 8
social dynamics : Friends enjoying dinner
emotional hooks : Social connection, Relaxed dining
--- Raw JSON ---
{"lifestyle_scene_overview_setting": "Outdoor restaurant patio", ...}
3. validate_metadata_schema
Validate metadata against schema requirements.
{
"metadata": {
"product_identification": {
"product_type": "Console Table",
"design_style": "Minimalist"
}
},
"schema_type": "product",
"strict_mode": false
}
4. create_xmp_packet
Generate standalone XMP packets.
{
"metadata": {
"scene_overview": {
"setting": "Modern office",
"activities": ["Working", "Collaboration"]
}
},
"output_path": "metadata/office_scene.xmp",
"pretty_print": true
}
5. create_metadata_report (NEW!)
Generate human-readable reports from XMP metadata with category organization.
{
"image_path": "processed/restaurant_scene_me.jpg",
"format": "detailed",
"include_raw_json": true
}
Category-Based Output:
🎯 TYPE OF ANALYSIS COMPLETED: LIFESTYLE
Categories Found: 8 | Total Fields: 14 | Processing Time: 4.2ms
📊 SCENE OVERVIEW
-----------------------------------------------------------------
Setting : Elegant restaurant interior
Time Of Day : Evening
👥 HUMAN ELEMENTS
-----------------------------------------------------------------
Number Of People: 6
Social Dynamics : Family celebration dinner
[... other organized categories ...]
=================================================================
RAW JSON DATA (Machine Readable)
=================================================================
{...complete metadata...}
Three Report Formats:
- detailed: Full categorized report with all metadata + raw JSON
- simple: Key fields organized by category for quick review
- json-only: Raw machine-readable metadata only
Supported Schemas
Lifestyle Schema (36+ fields)
Social dynamics, cultural context, and lifestyle analysis
scene_overview- Setting, time, occasion, activitieshuman_elements- Demographics, interactions, emotionsenvironment- Location, architecture, spatial arrangementmarketing_potential- Target demographics, brand alignment
Product Schema (25+ fields)
Design aesthetics and commercial product analysis
product_identification- Type, category, style, brandphysical_characteristics- Color, material, texture, dimensionscommercial_analysis- Market positioning, target market, pricingquality_assessment- Construction, materials, craftsmanship
Orbit Schema (40+ fields)
Comprehensive visual intelligence analysis
scene_overview- Setting, time, activities, moodhuman_elements- People count, age groups, interactionskey_objects- Products, technology, notable itemsatmospheric_elements- Color scheme, lighting, visual mood
Architecture
simple-orbit-mcp/
├── src/
│ ├── server.ts # Main MCP server
│ ├── core/
│ │ ├── supabase-client.ts # Stream-based storage client
│ │ ├── xmp-processor.ts # XMP creation and embedding
│ │ └── metadata-validator.ts # Schema validation
│ ├── tools/
│ │ ├── embed-metadata.ts # Embedding tool
│ │ ├── read-metadata.ts # Reading tool
│ │ ├── validate-schema.ts # Validation tool
│ │ ├── create-xmp.ts # XMP creation tool
│ │ └── create-metadata-report.ts # NEW! Category-based reports
│ └── types/
│ └── schemas.ts # TypeScript interfaces
└── dist/ # Compiled JavaScript
Development
Build and Watch
npm run build # Compile TypeScript
npm run watch # Watch for changes
npm run dev # Development mode with tsx
Environment Setup
# Required environment variables
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_ANON_KEY=your_anon_key_here
# Optional: Use service role key for enhanced permissions
SUPABASE_SERVICE_ROLE_KEY=your_service_role_key
Stream Processing Benefits
- ✅ No Local Storage: Images never touch your hard drive
- ✅ Memory Efficient: Process large images in RAM
- ✅ Fast Processing: Direct memory-to-memory operations
- ✅ Security: No local file persistence or cleanup needed
- ✅ Scalable: Works with any Supabase Storage bucket
Example Workflows
Lifestyle Image Analysis
# 1. Validate lifestyle metadata
validate_metadata_schema({
"metadata": {
"scene_overview": { "setting": "Coffee shop", "time_of_day": "Morning" },
"human_elements": { "number_of_people": 2, "social_dynamics": "Business meeting" }
},
"schema_type": "lifestyle"
})
# 2. Embed into image
embed_image_metadata({
"source_path": "uploads/coffee_meeting.jpg",
"metadata": { /* lifestyle metadata */ },
"output_path": "processed/coffee_meeting_analyzed.jpg"
})
# 3. Verify embedding
read_image_metadata({
"image_path": "processed/coffee_meeting_analyzed.jpg",
"format": "json"
})
Product Catalog Processing
# 1. Create XMP packet for product
create_xmp_packet({
"metadata": {
"product_identification": { "product_type": "Office Chair", "design_style": "Ergonomic" },
"commercial_analysis": { "target_market": ["Businesses", "Home offices"] }
},
"schema_type": "product",
"output_path": "metadata/office_chair.xmp"
})
# 2. Embed into product image
embed_image_metadata({
"source_path": "catalog/chair_001.jpg",
"metadata": { /* product metadata */ },
"output_path": "catalog/processed/chair_001_metadata.jpg"
})
Category-Based Report Generation
# 1. Generate detailed categorized report
create_metadata_report({
"image_path": "processed/restaurant_celebration_me.jpg",
"format": "detailed",
"include_raw_json": true
})
# Output: Organized report with category headers:
# 🎯 TYPE OF ANALYSIS COMPLETED: LIFESTYLE
# 📊 SCENE OVERVIEW | 👥 HUMAN ELEMENTS | 🌍 ENVIRONMENT
# 🍽️ KEY OBJECTS | 🌅 ATMOSPHERIC ELEMENTS | etc.
# 2. Generate simple summary report for quick review
create_metadata_report({
"image_path": "catalog/chair_001_me.jpg",
"format": "simple"
})
# Output: Condensed report showing key fields by category
# Analysis: PRODUCT (6 categories, 13 fields)
# 3. Generate JSON-only report for API integration
create_metadata_report({
"image_path": "orbit/workspace_me.jpg",
"format": "json-only"
})
✨ Enhanced Features Summary
Professional XMP Display
- Clean field names without schema prefixes
- Aligned formatting for consistent appearance
- Dual format: human-readable + machine-parseable
- ExifTool compatible output
📊 Category-Based Reports (NEW!)
- Metadata organized by natural categories (Scene Overview, Human Elements, etc.)
- Clear analysis type identification (LIFESTYLE/PRODUCT/ORBIT)
- Three report formats: detailed, simple, json-only
- Professional formatting with emoji headers and alignment
- Separated raw JSON section for machine processing
Smart Filename Management
- Automatic "_me" suffix for processed images
- Preserves original file organization
- Format conversion for universal XMP support
- Clear visual indicators of enhancement
Stream Processing
- Memory-only image processing
- No local file downloads or cleanup
- Fast, efficient operations
- Secure cloud-to-cloud processing
Dependencies
@modelcontextprotocol/sdk- MCP server framework@supabase/supabase-js- Supabase client for cloud storagesharp- High-performance image processing
Requirements
- Node.js 18+
- TypeScript 5+
- Supabase project with Storage bucket
- Valid Supabase credentials
Performance
- ✅ Sub-5ms Processing: Ultra-fast metadata embedding
- ✅ Memory Efficient: <256MB per request
- ✅ Format Conversion: Automatic PNG/TIFF → JPG optimization
- ✅ Smart Filenames: Instant visual feedback
- ✅ Beautiful Display: Professional XMP formatting
- ✅ 📊 Fast Reports: <5ms category-based report generation
- ✅ 🎯 Multi-Format: Detailed, simple, and JSON-only output formats
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
Support
If you encounter any issues or have questions, please open an issue on GitHub.
Image Metadata Embed and Report - Beautiful metadata, smart filenames, streamlined workflows
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。