What image formats are supported?
JPEG, TIFF, HEIC/AVIF, and PNG are supported.
@stass
基本情報
MCP server to extract image metadata (EXIF, XMP, etc)
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"exif-mcp": {
"command": "node",
"args": [
"/path/to/exif-mcp/dist/server.js"
]
}
}
}Reads all or specified metadata segments
Reads EXIF data specifically
Reads XMP data
Reads ICC color profile data
Reads IPTC metadata
Reads JFIF segment data
Reads IHDR segment data
Gets image orientation (1-8)
Gets rotation and flip information
Extracts GPS coordinates
Extracts embedded thumbnail
exif-mcp is a Model Context Protocol (MCP) server that enables LLMs to read image metadata on-demand, entirely offline. Built with TypeScript and powered by the exifr library, it parses metadata from common image formats without relying on any external tools, making it efficient and secure.
Install by cloning the repository, running npm install, and building with npm run build. For use with Claude Desktop, add an entry to claude_desktop_config.json with command: "node" and args: ["/path/to/exif-mcp/dist/server.js"]. The server can also be started with npm start or run in development mode with npm run dev. It uses StdioServerTransport and is compatible with any MCP client that supports STDIO transport.
JPEG, TIFF, HEIC/AVIF, and PNG are supported.
No. It works entirely offline and never makes remote network requests.
Image data can be supplied via a local file path (`path`), a URL (`url`), a base64 string (`base64`), or a base64 buffer (`buffer`).
It offers 11 tools: `read-metadata`, `read-exif`, `read-xmp`, `read-icc`, `read-iptc`, `read-jfif`, `read-ihdr`, `orientation`, `rotation-info`, `gps-coordinates`, and `thumbnail`.
Yes. It processes image metadata without executing any external tools or network calls, minimizing security risks. It also handles oversized payloads and internal exifr errors with standardized error handling.
A curated list of references for MLOps

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Hindsight: Agent Memory That Learns

Model Context Protocol Servers
コメント