広告掲載
MCP.so
ログイン

Florence-2 MCP Server

@jkawamoto

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

jkawamoto

Florence-2 MCP Server について

An MCP server for processing images using Florence-2

#python#florence-2#mcp-server

Florence-2 MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "florence-2": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jkawamoto/mcp-florence2",
        "mcp-florence2"
      ]
    }
  }
}

Florence-2 MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Florence-2 MCP Server?

An MCP (Model Context Protocol) server that processes images and PDF files using Microsoft’s Florence-2 model. It provides OCR to extract text and generates descriptive captions for images. Designed for developers and AI assistants (Claude, Goose, LM Studio) that need vision-based language model capabilities.

How to use Florence-2 MCP Server?

Install via the pre-built .mcpb bundle (for Claude Desktop) or by adding manual configuration entries to the claude_desktop_config.json, Goose config.yaml, or LM Studio MCP settings. All configurations use uvx to run the server from the Git repository. The server exposes two tools: ocr (extract text) and caption (generate captions), both accepting a src argument (file path or URL).

Key features of Florence-2 MCP Server

  • OCR for text extraction from images and PDFs
  • Image caption generation
  • Supports local file paths and remote URLs as input
  • Easy one‑click installs for Claude, Goose, and LM Studio
  • Runs via uvx for reproducible Python environments

Use cases of Florence-2 MCP Server

  • Extracting printed or handwritten text from scanned documents and photos
  • Generating alt‑text or summaries for images in a document workflow
  • Automating captioning of product images in an e‑commerce pipeline
  • Enabling voice‑assistant image analysis (e.g., reading a whiteboard photo aloud)
  • Integrating vision capabilities into LLM‑based AI agents without cloud dependencies

よくある質問

1

What model does the server use?

It uses Microsoft’s Florence‑2 (Florence‑2‑large) hosted on Hugging Face.

2

How do I install it?

For Claude Desktop, download the `.mcpb` bundle from the Releases page and open it. For Goose, use the provided deeplink or edit `~/.config/goose/config.yaml`. For LM Studio, click the “Add MCP Server” button in the README.

3

Can it process PDF files?

Yes. The OCR tool can extract text from PDFs as well as images.

4

What are the runtime requirements?

The server runs via `uvx`, so you need `uv` (or a Python environment with `uvx`). No additional Python package installation is required – `uvx` automatically fetches the dependencies.

5

Where does data processing happen?

All processing is performed locally on the user’s machine. The server reads image/PDF files from the local filesystem or fetches them from a provided URL.

コメント

「その他」の他のコンテンツ

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

der die das – German noun genders (Lingviko)

Lingviko

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.

The Living Bread

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

広告掲載