广告合作
MCP.so
登录

MCP Image Extractor

@ifmelate

代码仓库

基本信息

分类

媒体与设计

许可证

MIT

传输方式

stdio

作者

ifmelate

关于 MCP Image Extractor

MCP server which allow LLM in agent mode to analyze image whenever it needs

#image-extractor#image-processing#base64-converter

MCP Image Extractor 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "image-extractor": {
      "command": "node",
      "args": [
        "/full/path/to/mcp-image-extractor/dist/index.js"
      ],
      "disabled": false
    }
  }
}

MCP Image Extractor 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Image Extractor?

MCP Image Extractor is a Model Context Protocol server that extracts images from local files, URLs, or base64-encoded data and converts them to base64 for analysis by AI assistants. It is designed for developers who need to pass visual information to large language models (LLMs) within MCP-compatible tools like Cursor.

How to use MCP Image Extractor?

Install the server via npx in your .cursor/mcp.json configuration file (recommended), or clone the repository and build locally. Once configured, the server exposes three tools (extract_image_from_file, extract_image_from_url, extract_image_from_base64) that AI assistants can call automatically when instructed to analyze an image.

Key features of MCP Image Extractor

  • Extract images from local file paths
  • Extract images from remote URLs
  • Process base64-encoded image data
  • Automatic resizing to maximum 512x512 pixels
  • Easy one-line install with npx
  • Docker support for containerized deployments

Use cases of MCP Image Extractor

  • Analyze Playwright test result screenshots
  • Pass images from URLs to an LLM for description
  • Decode and analyze base64 image data
  • Integrate image analysis into AI assistant workflows

常见问题

1

What does MCP Image Extractor do?

It extracts images from local files, URLs, or base64 data and converts them to base64 so that an LLM (such as Claude) can analyze the visual content.

2

How do I install MCP Image Extractor?

The easiest method is to add a `npx -y mcp-image-extractor` command to your `.cursor/mcp.json` file. Alternatively, clone the repository, run `npm install && npm run build && npm link`, then reference the global command or the built file directly.

3

What tools does MCP Image Extractor provide?

It provides three tools: `extract_image_from_file` (accepts a `file_path`), `extract_image_from_url` (accepts a `url`), and `extract_image_from_base64` (accepts `base64` data and an optional `mime_type`).

4

Why are images resized to 512×512 pixels?

All extracted images are automatically resized to a maximum of 512×512 pixels to limit the base64 output size and optimize context‑window usage in LLM analysis.

5

How can I troubleshoot a “Failed to create client” error in Cursor?

If you see this error, try the local path installation method (pointing to the built `index.js` file) instead of the npx approach, or ensure the path to the executable is correct.

评论

媒体与设计 分类下的更多 MCP 服务器

agent-media

agent-media

Hosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.

Sleek

Sleek

Design your mobile app UI with AI, then have your coding agent build the real app from it.

aicut

aicut

Make AI videos, images, voiceovers and full AI Video Story episodes from Claude, ChatGPT, Cursor or any MCP client, then post them to TikTok, YouTube and Instagram. Veo, Kling, Seedance and more, on your own aicut accoun

InstantClips

InstantStudioAI

InstantClips turns an e-commerce product into short-form vertical video for TikTok, Instagram Reels and Stories. Import a product from its page URL or photos, generate on-brand video ads, and manage brands/products throu

SVGator

SVGator

Drive your SVGator account from any AI assistant. Prompt an animation, get an editable project back, and export it as SVG, Lottie, GIF, MP4, and more, then open it in the editor to finish by hand.

广告合作