MCPOfficialPaddlePaddle
PaddleOCR MCP
Recognizes text and parses documents with tables, formulas and handwriting.
The PaddleOCR project’s server exposes its OCR and document parsing pipelines: it extracts text, tables, formulas and handwriting from PDFs and images into an editable form. It runs locally (the [local-cpu] extra also installs the PaddlePaddle engine) or through an API: the official one on Baidu AI Studio (access token), Qianfan or your own PaddleOCR server.
Installation
Manual install
$pip install -U paddleocr-mcpDetails
- Works in
- Claude, VS Code
- Transport
- local
- License
- Apache-2.0
- Tasks
- Docs, Research
- Rating
- Source
- github.com/PaddlePaddle/PaddleOCR/tree/main/mcp_server (opens in a new tab)
Tags
- ocr
- tables
- handwriting
- paddleocr
A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.