Florence-2 MCP Server

An MCP server for processing images using Florence-2.

Installation

For Claude Desktop

To configure this server for Claude Desktop, edit the claude_desktop_config.json file with 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: For 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 to include 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: An MCP server for processing images using Florence-2
Command: uvx --from git+https://github.com/jkawamoto/mcp-florence2 mcp-florence2

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

Tools

ocr

Performs Optical Character Recognition (OCR) on the provided image file paths.

Arguments:

file_paths: A list of file paths to the image files to be processed.

ocr_urls

Processes image urls with OCR and returning recognized text.

Arguments:

urls: A list of urls to the image files that need to be processed.

caption

Generates detailed and descriptive captions for the provided image file paths.

Arguments:

file_paths: A list of file paths to the image files to be processed.

caption_urls

Generates detailed captions for a list of image urls.

Arguments:

urls: A list of urls to the image files that need to be processed.

License

This application is licensed under the MIT License. See the LICENSE file for more details.