mcp-mistral-ocr
If you are the rightful owner of mcp-mistral-ocr and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server that provides OCR capabilities using Mistral AI's OCR API, capable of processing both local files and URLs, supporting images and PDFs.
MCP Mistral OCR is a server designed to leverage Mistral AI's OCR API for processing optical character recognition tasks. It supports a variety of file formats including images and PDFs, and can handle files from both local directories and URLs. The server is containerized using Docker, ensuring easy deployment and scalability. It also integrates with UV package management for dependency handling. The results of OCR processing are saved as JSON files, complete with timestamps, making it easy to track and manage outputs. This server is particularly useful for applications requiring automated text extraction from documents and images, and it supports integration with platforms like Claude Desktop.
Features
- Process local files (images and PDFs) using Mistral's OCR
- Process files from URLs with explicit file type specification
- Support for multiple file formats (JPG, PNG, PDF, etc.)
- Results saved as JSON files with timestamps
- Docker containerization and UV package management
Tools
process_local_file
Process a file from the configured OCR_DIR directory.
process_url_file
Process a file from a URL. Requires explicit file type specification.
