RapidOCR MCP Server

September 13, 2025 · View on GitHub

A MCP server based on RapidOCR, providing an easy-to-use OCR interface.

Usage

uvx run rapidocr-mcp

MCP config

"rapidocr-mcp": {
    "command": "uvx",
    "args": [
    "rapidocr-mcp"
    ],
    "env": {}
}

Screenshots

config usage

Available Methods

ocr_by_content Perform OCR on an image content. Args: base64_data (str): The base64 encoded image content. Returns: List[TextContent]: A list of text content.
ocr_by_path Perform OCR on an image file. Args: path (str): The path to the image file. Returns: List[TextContent]: A list of text content.

remark

Currently, large language models are becoming increasingly powerful and generally possess multimodal capabilities, enabling them to recognize text in images without the need for external OCR tools.