MCP Florence2

🚀 Florence-2 MCP Server

An MCP server for processing images using Florence-2. It can handle images or PDF files stored locally or on a web server to extract text (OCR, Optical Character Recognition) or generate descriptive captions to summarize the image content.

🚀 Quick Start

This is an MCP server that uses Florence-2 to process images. You can process images or PDF files stored locally or on a web server to extract text (OCR, Optical Character Recognition) or generate descriptive captions to summarize the image content.

📦 Installation

For Claude Desktop

To configure this server in Claude Desktop, edit the claude_desktop_config.json file and add 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 details, refer to: Claude Desktop Users - Model Context Protocol.

For Goose CLI

To enable the Bear extension in Goose CLI, edit the configuration file ~/.config/goose/config.yaml and add the following entry:

extensions:
  bear:
    name: Florence-2
    cmd: uvx
    args: [ --from, git+https://github.com/jkawamoto/mcp-florence2, mcp-florence2 ]
    enabled: true
    type: stdio

For Goose Desktop

Add a new extension with the following settings:

• Type: Standard IO
• ID: florence-2
• Name: Florence-2
• Description: Florence-2 MCP server for processing images
• Command: uvx --from git+https://github.com/jkawamoto/mcp-florence2 mcp-florence2

For more details on configuring the MCP server in Goose Desktop, refer to the documentation: Using Extensions - MCP Servers.

📚 Documentation

ocr

Process an image file or URL using OCR to extract text.

Parameters:

• src: The path or URL of the image file to be processed.

caption

Process an image file and generate a textual caption for the image.

Parameters:

• src: The path or URL of the image file to be processed.

📄 License

This application is released under the MIT License. For more details, see the LICENSE file.