Metadata-Version: 2.4
Name: iflow-mcp_z4none-rapidocr-mcp
Version: 0.4.0
Summary: RapidOCR MCP Server for OCR processing
Project-URL: Homepage, https://github.com/z4none/rapidocr-mcp
Project-URL: Repository, https://github.com/z4none/rapidocr-mcp.git
Author-email: z4none <z4none@gmail.com>
License-Expression: MIT
License-File: LICENSE.txt
Keywords: mcp,ocr,rapidocr
Requires-Python: >=3.11
Requires-Dist: mcp[cli]>=1.4.1
Requires-Dist: onnxruntime>=1.21.0
Requires-Dist: rapidocr>=2.0.3
Requires-Dist: requests>=2.32.3
Description-Content-Type: text/markdown

# RapidOCR MCP Server

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

## Usage

```bash
uvx run rapidocr-mcp
```

## MCP config

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

## Screenshots

![config](/images/1.png)
![usage](/images/2.png)

## 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.