Summary
Connects Claude to Microsoft's Florence-2 vision model for local image processing. Exposes two tools: ocr for extracting text from images and PDFs, and caption for generating descriptive summaries of image content. Works with both local files and web URLs. Reach for this when you need offline OCR capabilities or want to generate alt text and image descriptions without hitting external APIs. Ships as a pre-built bundle that drops right into Claude Desktop, or runs via uvx for Goose and LM Studio. The model downloads locally on first run, so you own the processing pipeline end to end.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Florence-2 MCP Server
An MCP server for processing images using Florence-2.
You can process images or PDF files stored on a local or web server to extract text using OCR (Optical Character Recognition) or generate descriptive captions summarizing the content of the images.
Installation
Claude
Download the latest MCP bundle mcp-florence2.mcpb from
the Releases page,
then open the downloaded .mcpb file or drag it into the Claude Desktop's Settings window.
Manually configuration
You can also manually configure this server for Claude Desktop.
Edit the claude_desktop_config.json file by adding the following entry under mcpServers:
{
"mcpServers": {
"florence-2": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/jkawamoto/mcp-florence2",
"mcp-florence2"
]
}
}
}
After editing, restart the application.
For more information, see: Connect to local MCP servers - Model Context Protocol.
goose
Open this link
goose://extension?cmd=uvx&arg=--from&arg=git%2Bhttps%3A%2F%2Fgithub.com%2Fjkawamoto%2Fmcp-florence2&arg=mcp-florence2&id=florence2&name=Florence-2&description=An%20MCP%20server%20for%20processing%20images%20using%20Florence-2
to launch the installer, then click "Yes" to confirm the installation.
Manually configuration
You can also directly edit the config file (~/.config/goose/config.yaml) to include the following entry:
extensions:
florence2:
name: Florence-2
cmd: uvx
args: [ --from, git+https://github.com/jkawamoto/mcp-florence2, mcp-florence2 ]
enabled: true
type: stdio
For more details on configuring MCP servers in Goose, refer to the documentation: Using Extensions | goose.
LM Studio
To configure this server for LM Studio, click the button below.
Tools
ocr
Process an image file or URL using OCR to extract text.
Arguments:
- src: A file path or URL to the image file that needs to be processed.
caption
Processes an image file and generates captions for the image.
Arguments:
- src: A file path or URL to the image file that needs to be processed.
License
This application is licensed under the MIT License. See the LICENSE file for more details.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Registryactive
Packagehttps://github.com/jkawamoto/mcp-florence2/releases/download/v0.3.13/mcp-florence2.mcpb
TransportSTDIO
UpdatedMay 20, 2026