Polyglot document extraction with OCR
Extract text, metadata, and structured info from PDFs, Office docs, images, and 50+ formats. Multiple OCR backends including Tesseract, EasyOCR, PaddleOCR.
{
"mcpServers": {
"kreuzberg": {
"mcpServers": {
"kreuzberg": {
"args": [
"kreuzberg"
],
"command": "uvx"
}
}
}
}
}