Florence-2 MCP Server logo

Florence-2 MCP Server

by jkawamoto

The Florence-2 MCP Server processes images and PDF files using the Florence-2 model. It can extract text using OCR or generate descriptive captions summarizing the image content.

View on GitHub

Last updated: N/A

What is Florence-2 MCP Server?

This server is an MCP (Model Context Protocol) server that utilizes the Florence-2 model to process images and PDF files. It allows users to extract text from images using OCR or generate descriptive captions.

How to use Florence-2 MCP Server?

The server can be configured for use with Claude Desktop, Goose CLI, and Goose Desktop. Detailed installation instructions are provided in the README for each platform, involving editing configuration files to include the server's command and arguments.

Key features of Florence-2 MCP Server

  • OCR text extraction from images and PDFs

  • Image caption generation

  • Integration with Claude Desktop

  • Integration with Goose CLI

  • Integration with Goose Desktop

Use cases of Florence-2 MCP Server

  • Extracting text from scanned documents

  • Generating captions for images in a content management system

  • Automating image description for accessibility

  • Analyzing image content for research purposes

FAQ from Florence-2 MCP Server

What is Florence-2?

Florence-2 is a large language model developed by Microsoft for image understanding and generation.

What is OCR?

OCR stands for Optical Character Recognition, a technology that converts images of text into machine-readable text.

How do I install this server for Claude Desktop?

Edit the claude_desktop_config.json file with the provided configuration and restart the application.

How do I use the OCR tool?

Provide the src argument with the file path or URL of the image to be processed.

How do I use the caption tool?

Provide the src argument with the file path or URL of the image to be processed.