MCP for IIIF Images

MCP for IIIF Images

Provides tools to fetch IIIF manifests and retrieve specific image regions or scaled images for analysis. This server enables detailed interaction with International Image Interoperability Framework resources, supporting tasks like image description and transcription.

Category
访问服务器

README

MCP for IIIF Images

A Model Context Protocol (MCP) server for working with IIIF (International Image Interoperability Framework) manifests and images. See this video for a demonstration.

Features

This MCP server contains the following tools:

  • fetch_iiif_manifest: Fetch a IIIF manifest from a URL. (Note that clients may have difficulty processing large amounts of JSON.)
  • fetch_iiif_image: Retrieve a IIIF image from a base URI, fetching info.json and returning the image data (default: max 1500px dimension, max 800,000 pixels total)
  • fetch_iiif_image_region: Retrieve a specific region of a IIIF image using percentage coordinates, with the region scaled to fit within the same constraints

Caveats

  • The code scales the images to dimensions acceptable to Claude. It will not work with a Level 0 Image API implementation.
  • Claude may not process some IIIF Manifests due to the size of the file.

Claude Desktop Configuration

Install from Claude Desktop Extension (DXT) file

  1. Install and log in to Claude Desktop
  2. Download the .dxt file from the latest release
  3. Double-click the .dxt file
  4. Install the extension when prompted by Claude

Install from Source Code

  1. Clone this repository
  2. Install dependencies: npm install
  3. Make the server executable: chmod +x server/server.js

To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop config file. Adjust the file path as necessary. You may also need to provide the full path to your node command.

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-iiif-images": {
      "command": "node",
      "args": ["/PATH/TO/mcp-iiif-images/server/server.js"]
    }
  }
}

Windows

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-iiif-images": {
      "command": "node",
      "args": ["C:\\path\\to\\mcp-iiif-images\\server\\server.js"]
    }
  }
}

Linux

Edit ~/.config/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-iiif-images": {
      "command": "node",
      "args": ["/path/to/mcp-iiif-images/server/server.js"]
    }
  }
}

General MCP Usage

The server supports two transport modes:

Standard Mode (stdio)

Run the server using stdio transport (default):

npm start
# or
node server/server.js

HTTP Streaming Mode

Run the server using HTTP streaming transport:

node server/server.js --http
# or with custom port
node server/server.js --http --port 8080

Command-line Options

  • --http: Use HTTP streaming transport instead of stdio
  • --port PORT: Port number for HTTP server (default: 3000)
  • --help: Show help message

When using HTTP mode, the server will start an HTTP server with the following endpoints:

  • GET /sse: Establish Server-Sent Events connection
  • POST /messages?sessionId=<id>: Send MCP messages

HTTP Streaming Mode

For HTTP streaming mode, you'll need to start the server manually with the --http flag and then configure Claude Desktop to connect via HTTP:

node server/server.js --http --port 3000

Then configure Claude Desktop to use the HTTP transport (refer to Claude Desktop documentation for HTTP transport configuration).

Note: Update the path in the args array to match the actual location where you've installed this server.

After updating the configuration, restart Claude Desktop for the changes to take effect.

Testing

To run the tests:

# Run tests once
npm test

# Run tests in watch mode (automatically re-runs on file changes)
npm run test:watch

# Run tests with coverage
npm test -- --coverage

The project uses Vitest as the testing framework, which provides:

  • Fast execution with ES modules support
  • Jest-compatible API with better error messages
  • Built-in coverage reporting
  • Watch mode for development

Available Tools

fetch_iiif_manifest

Fetches and validates a IIIF manifest from a URL.

Parameters:

  • url (required): The URL of the IIIF manifest to fetch

Example usage:

Please fetch the IIIF manifest from https://example.com/manifest.json

fetch_iiif_image

Retrieve a IIIF image from a base URI, fetching info.json and returning the image data.

Parameters:

  • baseUri (required): Base URI of the IIIF Image API resource (without /info.json)

Example usage:

Fetch the IIIF image at https://example.com/iiif/image123

fetch_iiif_image_region

Retrieve a specific region of a IIIF image using percentage coordinates, with the region scaled to fit within the same constraints. Use this to fetch regions of interest at higher detail for more accurate image description and analysis.

Parameters:

  • baseUri (required): Base URI of the IIIF Image API resource (without /info.json)
  • region (required): Region in pct: format (e.g., 'pct:20,20,50,50' for x,y,width,height as percentages)

Example usage:

Fetch a region from the IIIF image at https://example.com/iiif/image123 with region pct:10,10,50,50

Note that you can use these tools together in the course of a conversation, for example:

Fetch the IIIF image at https://example.com/iiif/image123 and describe it.
...
Zoom in on the text at the bottom of the page and transcribe it.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选