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

For Claude Desktop

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.

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: 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.

For 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.