Mcp Florence2

io.github.jkawamoto由 GitHub 账号 jkawamoto 发布v0.5.4更新于 Nov 14, 2026

An MCP server for processing images using Florence-2

已验证STDIO仅桌面文件与存储媒体与设计

概览

AI 生成的概览

在本地运行微软 Florence-2 视觉模型,让助手对图片和多页 PDF 做 OCR、生成描述并执行自定义视觉任务。

可以做什么
  • 从图片或多页 PDF 中逐页提取全部可见文字
  • 生成详细描述,涵盖物体、空间关系、颜色与背景
  • 执行自定义 Florence-2 任务提示,如目标检测、区域描述与边界框
  • 输入源可以是本地文件路径或 HTTP/HTTPS 网址
适用场景
适合需要从扫描件、发票或截图中读取文字,或描述图片内容,又不希望把文件发送到外部视觉 API 的场景。配有 GPU 或 Apple Silicon 的桌面环境可获得更快推理速度。
运行要求
以本地 stdio 进程运行,通常用 uvx 启动或在 Claude Desktop 中安装 .mcpb 包;仅支持桌面端。需下载 Hugging Face 上的 Florence-2 模型(默认 large,可选 base),需要 Python 与 uv,以及足够的磁盘、内存或 GPU;仅在处理网址时需要对外 HTTP 访问。可通过 HTTP_PROXY、HTTPS_PROXY、NO_PROXY 配置代理。
安装前请注意
处理 http 或 https 网址时服务器进程会发起对外请求,README 警告在不可信用户或提示可提供网址的环境中可能遭受服务端请求伪造(SSRF),指向内网服务或云元数据端点;不可信或多租户环境应使用防 SSRF 的转发代理。交给工具的文件与网址会被本地模型读取,首次运行会从 Hugging Face 下载模型权重。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Florence2,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

English | 日本語

Florence-2 MCP Server

[uv] [Python Version] [Python Application] [pre-commit] [GitHub License]

[MseeP.ai Security Assessment Badge]

Florence-2 MCP Server brings local vision intelligence and Optical Character Recognition (OCR) to your AI assistants via the Model Context Protocol (MCP). Powered by Microsoft's Florence-2 foundation model, it lets your LLMs inspect, caption, and extract text from local images, web URLs, and multi-page PDF documents — entirely offline and on your own machine.


✨ Key Features

  • 🔒 100% Local & Private: All image and document processing runs on your local machine. No external vision API fees, token limits, or data sharing.
  • 📄 Multi-Page PDF & Image Support: Process common image formats (JPEG, PNG, WebP, etc.) as well as multi-page PDF documents page-by-page.
  • ⚡ Native Hardware Acceleration: Automatically detects and leverages Apple Silicon (MPS), NVIDIA GPU (CUDA), or CPU.
  • 🧹 Zero VRAM Waste: By default, inference runs in an on-demand subprocess to release VRAM immediately after completion. A --cache-model flag is available for low-latency continuous usage.
  • 🎯 Rich Vision Tasks: Perform high-precision text OCR, detailed descriptive captioning, and open-ended visual queries using native Florence-2 prompt tokens (e.g. object detection, region descriptions).
  • 📦 One-Click Installs: Ready-to-use .mcpb bundle for Claude Desktop, 1-click deeplink for LM Studio, and extension support for Goose.

🚀 Quick Installation

Choose your preferred MCP client below:

Claude Desktop

Option 1: One-Click Extension Bundle (Recommended)
  1. Download the latest mcp-florence2.mcpb bundle from the Releases page.
  2. Double-click the downloaded .mcpb file, or drag-and-drop it into Claude Desktop's Settings window.
Option 2: Manual Configuration

Add the following configuration to your claude_desktop_config.json:

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

[!NOTE] Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

For more details, see Connect to local MCP servers.


Goose

Option 1: One-Click URL

Click the link below to launch the Goose extension installer:

text
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
Option 2: Manual Configuration

Add the following to ~/.config/goose/config.yaml:

yaml
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, refer to Using Extensions | goose.


LM Studio

Click the button below to install directly into LM Studio:

[Add MCP Server florence-2 to LM Studio]


Claude Code, Cursor, Cline & Other MCP Clients

You can connect any client that supports stdio MCP servers using uvx:

bash
uvx --from git+https://github.com/jkawamoto/mcp-florence2 mcp-florence2

🛠️ Tools

The server automatically equips your AI assistant with the following vision capabilities. You can interact with them using natural language:

1. ocr

Extracts all visible text from images or multi-page PDF documents.

  • Example user request: "Please extract all text from /path/to/invoice.pdf."
  • Multi-page support: Automatically iterates through every page in a PDF document.
Tool schema & parameters
ParameterTypeRequiredDescription
srcstringYesLocal file path or HTTP/HTTPS URL of an image or PDF file.

2. caption

Generates comprehensive, detailed captions describing what is depicted in the image.

  • Example user request: "Describe what is shown in https://example.com/photo.jpg."
  • Returns granular descriptions of objects, spatial relationships, colors, and background scenery.
Tool schema & parameters
ParameterTypeRequiredDescription
srcstringYesLocal file path or HTTP/HTTPS URL of an image or PDF file.

3. process

Executes custom Florence-2 task prompts directly against the input image or PDF for advanced computer vision workflows (such as object detection or region captioning).

  • Example user request: "Detect all objects in this image and return their bounding boxes."
Tool schema & supported task prompts
Parameters
ParameterTypeRequiredDescription
srcstringYesLocal file path or HTTP/HTTPS URL of an image or PDF file.
promptstringYesTask prompt specifying the operation to perform.
Supported Florence-2 Task Prompts
Task PromptDescription
<CAPTION>Concise one-sentence summary of the image.
<DETAILED_CAPTION>Moderate-length description of the image content.
<MORE_DETAILED_CAPTION>Highly detailed and exhaustive scene description.
<OCR>Plain text extraction from the image.
<OCR_WITH_REGION>Text extraction along with bounding box coordinates.
<OD>Object detection (identifies objects and their bounding boxes).
<DENSE_REGION_CAPTION>Generates descriptions for multiple distinct regions.
<REGION_PROPOSAL>Identifies candidate bounding boxes for prominent visual regions.

⚙️ Configuration & CLI Options

The server can be customized using command-line arguments:

bash
mcp-florence2 [OPTIONS]
OptionTypeDefaultDescription
--modelstringflorence-community/Florence-2-largeHugging Face model identifier to load.
--cache-modelflagfalseKeeps the model in VRAM for faster repeated calls (by default, models run in subprocesses to free memory when idle).
--versionflag-Show version information.
--helpflag-Show help message and exit.

Using a Smaller / Faster Model

If you have limited GPU memory or want faster execution, switch to Florence-2-base:

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

🛡️ Security Considerations

When processing URLs starting with http:// or https://, outbound HTTP requests are initiated directly from the server process. In environments where untrusted users or prompts may supply URLs, this could potentially expose the server to Server-Side Request Forgery (SSRF) targeting internal network services or cloud metadata endpoints.

[!WARNING] In multi-tenant or untrusted environments, route outgoing HTTP(S) traffic through an SSRF-safe forward proxy (such as Smokescreen or Squid configured to block private/internal IP ranges).

Since Python's requests library automatically respects standard environment variables, proxy settings can be configured directly in your client configuration:

  • HTTP_PROXY / http_proxy: Proxy URL for HTTP requests.
  • HTTPS_PROXY / https_proxy: Proxy URL for HTTPS requests.
  • NO_PROXY / no_proxy: Comma-separated list of hosts to bypass the proxy.
Proxy Configuration Examples
Claude Desktop

Add the env block to claude_desktop_config.json:

json
{  "mcpServers": {    "florence-2": {      "command": "uvx",      "args": [        "--from",        "git+https://github.com/jkawamoto/mcp-florence2",        "mcp-florence2"      ],      "env": {        "HTTP_PROXY": "http://proxy.example.com:8080",        "HTTPS_PROXY": "http://proxy.example.com:8080"      }    }  }}
Goose

Add the env block to ~/.config/goose/config.yaml:

yaml
extensions:  florence2:    name: Florence-2    cmd: uvx    args: [ --from, git+https://github.com/jkawamoto/mcp-florence2, mcp-florence2 ]    env:      HTTP_PROXY: "http://proxy.example.com:8080"      HTTPS_PROXY: "http://proxy.example.com:8080"    enabled: true    type: stdio

💻 Development

Setup & Run Tests

This project uses uv for fast, reliable dependency management.

bash
# Clone the repositorygit clone https://github.com/jkawamoto/mcp-florence2.gitcd mcp-florence2
# Install dependencies and run testsuv run pytest
# Run pre-commit checksuv run pre-commit run --all-files

📄 License

This application is released under the MIT License.

来源:README.md,提交 335b6df

工具

0
SourceWeft 曾在隔离沙箱中以无凭据方式启动该软件包一次,以列出其工具,但未能完成:该软件包类型无法在沙箱中运行。

版本历史

5
  1. v0.5.4最新Nov 14, 2026
  2. v0.5.3Oct 29, 2026
  3. v0.5.2Oct 21, 2026
  4. v0.5.1Oct 1, 2026
  5. v0.5.0Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分