PaddleOCR
by PaddlePaddle
Official listing: built and published by Baidu. More from Baidu
Converts documents, receipts, and images into structured data with OCR, layout analysis, and table recognition, exposed to agents via a Python API, CLI, and MCP server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with PaddleOCR connected:
- Text Recognition
Use PaddleOCR to extract printed and handwritten text from images and scanned PDFs: ‹what you need›
- Layout Analysis
Use PaddleOCR to detect document structure: ‹what you need›
- Table Recognition
Use PaddleOCR to parse tables from scans into structured HTML or Markdown: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"paddleocr": {
"command": "uvx",
"args": [
"--from",
"paddleocr-mcp",
"paddleocr_mcp"
]
}
}
}claude mcp add paddleocr -- uvx --from paddleocr-mcp paddleocr_mcp
It runs on your computer, so web assistants such as Grok and ChatGPT can’t start it.
Its page: paddleocr.com
Install the CLI
python -m pip install paddleocr
Its page: paddleocr.com
Call the API
Auth None needed
Its page: paddleocr.com
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLIMCP
- Auth
- None
- Skills
- 4
Skills
Text Recognition
Extracts printed and handwritten text from images and scanned PDFs across more than 80 languages.
Layout Analysis
Detects document structure including headings, paragraphs, figures, and reading order before extraction.
Table Recognition
Parses tables from scans into structured HTML or Markdown while preserving row and column spans.
Document Pipeline
Runs end-to-end pipelines chaining detection, recognition, and structure parsing into JSON output.
