PaddleOCR

GitHub

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

86,141 stars Python 1 file · ~5,410 tokens #ai4science #chineseocr #document-parsing #document-translation #kie #ocr #paddleocr-vl #pdf-extractor-rag

PaddleOCR MCP Server

MCP server for PaddlePaddle/PaddleOCR

Ready-to-Use Client Configurations

{
  "mcpServers": {
    "PaddleOCR": {
      "command": "npx",
      "args": [
        "-y",
        "@PaddlePaddle/PaddleOCR"
      ]
    }
  }
}

{
  "mcpServers": {
    "PaddleOCR": {
      "command": "npx",
      "args": [
        "-y",
        "@PaddlePaddle/PaddleOCR"
      ]
    }
  }
}

{
  "mcpServers": {
    "PaddleOCR": {
      "command": "npx",
      "args": [
        "-y",
        "@PaddlePaddle/PaddleOCR"
      ]
    }
  }
}

{
  "mcpServers": {
    "PaddleOCR": {
      "command": "npx",
      "args": [
        "-y",
        "@PaddlePaddle/PaddleOCR"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "PaddleOCR": {
      "command": "npx",
      "args": [
        "-y",
        "@PaddlePaddle/PaddleOCR"
      ]
    }
  }
}

docker run -i --rm mcp/PaddleOCR