The Oxenstierna project aims to provide functions for searching, obtaining, and analyzing archive content by integrating multiple APIs (such as OAIPMH, IIIF, and Search API) of the Swedish National Archives, including the HTR (Handwritten Text Recognition) process and image processing.

An OCR service based on Mistral AI, supporting text and image recognition of local files and URLs

An MCP server based on the xAI Grok API, providing AI image analysis functions, supporting image description, metadata extraction, and OCR text recognition for URLs and local files.

An MCP server based on Google Gemini AI that provides image, audio, and video recognition functions, supporting multiple transmission methods and client integration.

This is a fashion recommendation system based on CLIP. It detects the clothing pictures uploaded by users through YOLO and recommends similar products after encoding with CLIP. The project has completed the construction of the FastAPI server, database connection, and basic front - end UI. The next step is to optimize the label accuracy of CLIP and system integration.

An MCP server that provides image recognition functions, supporting the visual APIs of Anthropic and OpenAI, with capabilities such as image description, multi - format support, configurable primary - backup service providers, and OCR text extraction.

This project aims to provide access to the content of the Swedish National Archives (Riksarkivet) through multiple API interfaces (such as OAI - PMH, IIIF, and Search API), including functions such as searching for records, obtaining collection information, downloading images, etc., and exploring the real - time handwritten text recognition (HTR) process.

The TextIn MCP Server is a document text extraction and OCR tool that supports text recognition, key information extraction, and conversion to Markdown format from images, PDFs, and Word documents.

The OpenCV MCP Server is a Python - based computer vision service that provides OpenCV's image and video processing capabilities through the Model Context Protocol (MCP). It offers a full set of computer vision tools from basic image processing to advanced object detection for AI assistants and language models, including image processing, edge detection, face recognition, video analysis, and real - time object tracking.

MCP Image Processing Service Based on Florence-2

A fashion recommendation system based on CLIP that realizes similar product recommendations through image recognition and encoding.

The Grok AI MCP Server is a Node.js - based server that integrates the xAI Grok API, providing powerful AI - driven analysis tools for the Solana blockchain. It supports transaction analysis, address analysis, image analysis, and general queries, and provides a standardized interface through the Model Context Protocol (MCP).

An image recognition server based on the Model Context Protocol that provides image analysis and description functions through OpenAI-compatible vision models, supporting cloud and local model integration.

An image editing MCP service based on Rust, providing functions such as image recognition, cropping, rotation, OCR text extraction, AI generation, and editing, and supporting integration into AI assistants through the MCP protocol.

The MCP server for handwriting OCR, which integrates with the Handwriting OCR API and supports uploading image/PDF documents, checking status, and obtaining OCR recognition results.

An AI-based food nutritional analysis assistant that identifies foods through images, calculates calorie and protein content, and supports nutritional knowledge Q&A and conversation memory functions.

The Douyin and Xiaohongshu Content Extraction MCP Server supports extracting video, image, and text content from Douyin and Xiaohongshu sharing links, providing functions such as watermark-free video acquisition, AI speech recognition, and text extraction.

BenBox is an AI agent system based on the SSE-based MCP protocol, including a mobile Angular application, supporting image recognition and cloud deployment.