exif-mcp
Offline MCP server for fast, flexible image metadata extraction.
Key Features
Use Cases
README
exif-mcp
An MCP server that allows LLMs (or humans) to read image metadata on-demand, entirely offline. Based on the excellent exifr library it's exremely fast and does not rely on any external tools.
Usecases:
- Analyze image metadata and visualize it
- Perform analysis of your image library: what are my most used cameras? Lens distribution? Which dates of the week I take most pictures on? Most favorite locations?
- Debugging image manipulation code.
Ths tool is used extensively by the reverse geolocation service PlaceSpotter for development and testing.
Overview
exif-mcp is a Model Context Protocol (MCP) server that provides tools for extracting various metadata segments from images. Built with TypeScript, it leverages the excellent exifr library to parse metadata from images in common formats like JPEG, PNG, TIFF, and HEIC. This allows this service to parse image metadata without executing any external tools which allows it to be both highly efficient and secure.
Features
- Local operation: Works completely offline with no remote network required
- Multiple segments: Extracts EXIF, GPS, XMP, ICC, IPTC, JFIF, and IHDR metadata
- Various input formats: Supports JPEG, TIFF, HEIC/AVIF, and PNG
- Flexible image sources: Read from file system, URLs, base64 data, or buffers
- Specialized tools: Get orientation, rotation info, GPS coordinates, and thumbnails
Installation
# Clone the repository
git clone https://github.com/stass/exif-mcp.git
cd exif-mcp
# Install dependencies
npm install
# Build the project
npm run build
Usage
Claude Desktop
Put this into Claude config file (claude_desktop_config.json):
"mcpServers": {
"exif-mcp": {
"command": "node",
"args": [
"/path/to/exif-mcp/dist/server.js"
]
}
},
Restart Claude. Now you can ask Claude to inspect images for you or e.g. find files taken with specific camera. This works best in combination with filesystem MCP tools so Claude can find files and list directories.
Starting the server
# Start the server
npm start
# For development with auto-reload
npm run dev
The server uses the StdioServerTransport from the MCP SDK, making it compatible with any MCP client that supports STDIO transport.
You can use mcp-proxy to enable remote access.
Available Tools
The following tools are provided by the server:
| Tool name | Description |
|---|---|
read-metadata |
Reads all or specified metadata segments |
read-exif |
Reads EXIF data specifically |
read-xmp |
Reads XMP data |
read-icc |
Reads ICC color profile data |
read-iptc |
Reads IPTC metadata |
read-jfif |
Reads JFIF segment data |
read-ihdr |
Reads IHDR segment data |
orientation |
Gets image orientation (1-8) |
rotation-info |
Gets rotation and flip information |
gps-coordinates |
Extracts GPS coordinates |
thumbnail |
Extracts embedded thumbnail |
Debugging with MCP Inspector
- Start the inspector:
npx @modelcontextprotocol/inspector node dist/server.js - Connect to it with MCP Inspector using the STDIO transport
- Call a tool, e.g.,
read-metadatawith parameter:json{ "image": { "kind": "path", "path": "/path/to/image.jpg" } } - You cal also use MCP inspector command line like this:
npx @modelcontextprotocol/inspector --cli node dist/server.js --method tools/call --tool-name read-exif --tool-arg image='{"kind": "path", "path": "/path/to/image.jpeg"}' --tool-arg pick="[]"
Image Source Types
The server supports multiple ways to provide image data:
// From local file system
{
"kind": "path",
"path": "/path/to/image.jpg"
}
// From URL (http, https, or file://)
{
"kind": "url",
"url": "https://example.com/image.jpg"
}
// From base64 data (raw or data URI)
{
"kind": "base64",
"data": "data:image/jpeg;base64,/9j/4AAQSkZ..."
}
// From base64 buffer
{
"kind": "buffer",
"buffer": "/9j/4AAQSkZ..."
}
Development
Running Tests
# Run tests
npm test
# Run tests with watch mode
npm run test:watch
Project Structure
exif-mcp/
├── src/
│ ├── server.ts # Main entry point
│ ├── tools/
│ │ ├── index.ts # Tool registration
│ │ ├── loaders.ts # Image loading utilities
│ │ └── segments.ts # exifr options builders
│ └── types/
│ └── image.ts # Type definitions
├── tests/ # Test files
└── README.md
Error Handling
The server provides standardized error handling for common issues:
- Unsupported formats or missing metadata
- Network fetch failures
- Oversized payloads
- Internal exifr errors
License
BSD 2-clause
Acknowledgements
- exifr - Extremely fast and robust EXIF parsing library
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
MCP Server Giphy
MCP-compatible Giphy API server for AI models to search and retrieve GIFs.
MCP Server Giphy provides an MCP-compliant server interface for accessing GIFs from the Giphy API, specifically tailored for seamless integration with AI models. It supports content filtering, multiple retrieval methods (search, trending, random), and optimized response formats with comprehensive metadata. The server enables AI applications to search, retrieve, and utilize GIF content efficiently, and is easily configurable with tools like Claude Desktop.
- ⭐ 22
- MCP
- magarcia/mcp-server-giphy
Exa MCP Server
Fast, efficient web and code context for AI coding assistants.
Exa MCP Server provides a Model Context Protocol (MCP) server interface that connects AI assistants to Exa AI’s powerful search capabilities, including code, documentation, and web search. It enables coding agents to retrieve precise, token-efficient context from billions of sources such as GitHub, StackOverflow, and documentation sites, reducing hallucinations in coding agents. The platform supports integration with popular tools like Cursor, Claude, and VS Code through standardized MCP configuration, offering configurable access to various research and code-related tools via HTTP.
- ⭐ 3,224
- MCP
- exa-labs/exa-mcp-server
MCP OpenNutrition
Provides local, privacy-preserving access to a comprehensive food and nutrition database via the Model Context Protocol.
MCP OpenNutrition is a Model Context Protocol (MCP) server offering access to a large, authoritative nutrition database with over 300,000 food items sourced from trusted public datasets. It enables searching by name, browsing, detailed nutritional lookups by ID, and barcode scanning, all running locally for privacy and low latency. The tool is designed for seamless integration with AI systems that follow the MCP standard, such as Claude/Cline, to enhance food and nutrition query capabilities.
- ⭐ 134
- MCP
- deadletterq/mcp-opennutrition
JSON MCP Filter
MCP server for JSON schema generation, smart filtering, and secure chunked data extraction.
JSON MCP Filter is an MCP-compliant server offering robust JSON schema generation and field-level filtering tools for both local files and remote HTTP/HTTPS endpoints. Leveraging quicktype for precise TypeScript type creation, it supports advanced features such as smart shape-based filtering, auto-chunking of large datasets, and memory-safe processing. Designed for seamless integration with popular MCP clients, it excels at extracting and preparing relevant JSON data for large language model contexts.
- ⭐ 17
- MCP
- kehvinbehvin/json-mcp-filter
PDF Tools MCP
Comprehensive PDF manipulation via MCP protocol.
PDF Tools MCP provides an extensive suite of PDF manipulation operations using the Model Context Protocol framework. It supports both local and remote PDF tasks, such as rendering pages, merging, extracting metadata, retrieving text, and combining documents. The tool registers endpoints through the MCP protocol, enabling seamless server-based PDF processing for various clients. Built with Python, it emphasizes secure handling and compatibility with Claude Desktop via the Smithery ecosystem.
- ⭐ 31
- MCP
- danielkennedy1/pdf-tools-mcp
mcp-server-webcrawl
Advanced search and retrieval for web crawler data via MCP.
mcp-server-webcrawl provides an AI-oriented server that enables advanced filtering, analysis, and search over data from various web crawlers. Designed for seamless integration with large language models, it supports boolean search, filtering by resource types and HTTP status, and is compatible with popular crawling formats. It facilitates AI clients, such as Claude Desktop, with prompt routines and customizable workflows, making it easy to manage, query, and analyze archived web content. The tool supports integration with multiple crawler outputs and offers templates for automated routines.
- ⭐ 32
- MCP
- pragmar/mcp-server-webcrawl
Didn't find tool you were looking for?