Image Extractor

MCP server for extracting and converting images to base64 for LLM analysis.

This MCP server provides tools for AI assistants to:

- Extract images from local files
- Extract images from URLs
- Process base64-encoded images

- analyze playwright test results: screenshots

Recommended: Using npx in mcp.json (Easiest)

The recommended way to install this MCP server is using npx directly in your.cursor/mcp.jsonfile:

{ "mcpServers": { "image-extractor": { "command": "npx", "args": [ "-y", "mcp-image-extractor" ] } } }

- Automatically installs the latest version
- Does not require global installation
- Works reliably across different environments

If you prefer to use a local installation of the package, you can clone the repository and point to the built files:

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

# Clone and install git clone https://github.com/ifmelate/mcp-image-extractor.git cd mcp-image-extractor npm install npm run build npm link

This will make themcp-image-extractorcommand available globally.

{ "mcpServers": { "image-extractor": { "command": "mcp-image-extractor", "disabled": false } } }

Troubleshooting for Cursor Users: If you see "Failed to create client" error, try the local path installation method above or ensure you're using the correct path to the executable.

Extracts an image from a local file and converts it to base64.

- file_path(required): Path to the local image file

Note:All images are automatically resized to optimal dimensions (max 512x512) for LLM analysis to limit the size of the base64 output and optimize context window usage.

Extracts an image from a URL and converts it to base64.

- url(required): URL of the image to extract

Note:All images are automatically resized to optimal dimensions (max 512x512) for LLM analysis to limit the size of the base64 output and optimize context window usage.

Processes a base64-encoded image for LLM analysis.

- base64(required): Base64-encoded image data
- mime_type(optional, default: "image/png"): MIME type of the image

Note:All images are automatically resized to optimal dimensions (max 512x512) for LLM analysis to limit the size of the base64 output and optimize context window usage.

Here's an example of how to use the tools from Claude:

Please extract the image from this local file: images/photo.jpg

Claude will automatically use theextract_image_from_filetool to load and analyze the image content.

Please extract the image from this URL: https://example.com/image.jpg

Claude will automatically use theextract_image_from_urltool to fetch and analyze the image content.

docker build -t mcp-image-extractor . docker run -p 8000:8000 mcp-image-extractor

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

next-devtools-mcp is a MCP server that provides Next.js development tools and utilities for AI coding assistants like Claude and Cursor.

Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com.

A demonstration server for ActionKit, providing access to Slack actions via Claude Desktop.

MCP server that lets Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions, and async jobs.

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

A Python MCP package that gives your LLM agents complete file system and shell capabilities — production-ready, sandboxed, and wired to any LLM in minutes.

Integrates with Google AI Studio/Gemini API for PDF to Markdown conversion and content generation.

Anchor Browser (https://anchorbrowser.io) is secure infrastructure for computer-use agents — stealth cloud browsers, authentication, captcha bypass, and a hosted MCP server for Cursor, Claude, and Windsurf.