MCP Image Extractor

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

FAQ from MCP Image Extractor

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.

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.

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).

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.

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.