Image Processor Mcp
@pansuriyadhvanil
An MCP server that provides tools for downloading, compressing, optimizing images, and extracting text via OCR. Built using the Model Context Protocol (MCP), this server enables AI assistants to download images from URLs or search, compress and convert images with various format
概要
What is Image Processor Mcp?
Image Processor Mcp is a Model Context Protocol server that provides tools for downloading, compressing, optimizing images, and extracting printed text via OCR. It enables AI assistants to perform these tasks programmatically, supporting operations like batch processing, format conversion, and filename synchronization.
How to use Image Processor Mcp?
Install Node.js 18 or higher, then configure the server with an MCP host. Use the provided tools—download_image, compress_image, compress_directory, sync_filenames, extract_text, and get_acknowledgement—by passing required parameters. An optional IMAGE_SEARCH_API_KEY environment variable enables keyword-based image search via Pexels.
Key features of Image Processor Mcp
- Download images from URLs or search by keyword (Pexels integration)
- Compress/convert single images to 10 output formats (WebP, AVIF, JPEG, etc.)
- Recursive compression to target file size with configurable quality and effort
- Batch process entire directories preserving folder structure with auto-generated reports
- Sync filename references across project files after compression
- Extract printed text via local OCR (100+ languages, no cloud calls)
Use cases of Image Processor Mcp
- Compress and convert images for web performance optimization
- Batch convert an entire image directory to WebP with automatic report generation
- Update all filenames in source code (HTML, CSS, JS) after converting PNG to WebP
- Extract printed text from scanned documents or screenshots
- Download high-quality images from Pexels and immediately resize and compress them
FAQ from Image Processor Mcp
What output formats are supported for image compression?
The server supports 10 formats: WebP, AVIF, JPEG, PNG, TIFF, GIF, HEIF, JPEG 2000, JPEG XL, and PDF.
Can OCR extract handwritten text?
No—Tesseract OCR is designed for printed text only. Handwritten text is not supported.
Where are auto-generated reports saved?
All reports and mapping files are stored in a .image-processor-mcp/ directory at the project root, organized into reports/, mappings/, and syncs/ subdirectories.
What are the system requirements?
Node.js version 18 or higher and an NPM-compatible package manager. No external APIs are needed except for image search (optional Pexels key).
How does filename synchronization ensure safety?
sync_filenames validates that the mapping JSON file is timestamp-paired with a compression report before applying any replacements. It also supports dry-run mode to preview changes.