Florence-2 MCP
An MCP server for processing images using Florence-2 that brings local vision intelligence and Optical Character Recognition (OCR) to AI assistants. It allows LLMs to inspect, caption, and extract text from local images, web URLs, and multi-page PDF documents entirely offline on the user's machine, supporting hardware acceleration via Apple Silicon, NVIDIA GPU, or CPU.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Perform high-precision text OCR on images and documents
- Generate detailed descriptive captions for visual content
- Extract text from multi-page PDF documents page-by-page
- Answer open-ended visual queries using Florence-2 prompt tokens
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/jkawamoto/mcp-florence2/releases/download/v0.5.3/mcp-florence2.mcpb 0.5.3
{
"version": "0.5.3",
"transport": "stdio",
"fileSha256": "a5358e7251cc3be7b032a53c72fbcdb8dad7c886dc8f917703a1914258660eb4",
"identifier": "https://github.com/jkawamoto/mcp-florence2/releases/download/v0.5.3/mcp-florence2.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like Florence-2 MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.