PaddleOCR MCP server

This MCP server implements the Model Context Protocol for PaddleOCR, allowing you to easily deploy and access OCR functionality through a standardized API interface. It simplifies the process of integrating PaddleOCR's powerful text recognition capabilities into your applications.

Installation

Prerequisites

Before installing the PaddleOCR MCP server, ensure you have the following dependencies:

• Python 3.7+
• pip (Python package manager)

Setting Up the Environment

First, clone the repository and install the required packages:

# Clone the repository
git clone https://github.com/PaddlePaddle/PaddleOCR.git
cd PaddleOCR

# Install dependencies
pip install -r requirements.txt
pip install paddleocr

Installing Additional Requirements

For the MCP server specifically, you may need additional packages:

pip install fastapi uvicorn

Usage

Starting the Server

To start the PaddleOCR MCP server:

python mcp_server.py --port 8080

You can customize the port number according to your needs.

Configuration Options

The server supports several configuration options:

python mcp_server.py --help

Common configuration parameters include:

• --port: Port number (default: 8000)
• --host: Host address (default: 0.0.0.0)
• --model_path: Path to custom OCR model
• --use_gpu: Enable GPU acceleration (default: False)

API Endpoints

The MCP server exposes several API endpoints:

• /v1/models: List available models
• /v1/completions: Process OCR requests

Example Request

Here's an example of sending an OCR request to the server:

curl -X POST "http://localhost:8080/v1/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paddleocr",
    "image": "base64_encoded_image_string",
    "parameters": {
      "language": "ch"
    }
  }'

Processing Results

The server returns OCR results in JSON format:

{
  "id": "cmpl-123abc",
  "object": "text_completion",
  "created": 1677858164,
  "model": "paddleocr",
  "choices": [
    {
      "text": "Detected text content",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 16,
    "total_tokens": 17
  }
}

Troubleshooting

Common Issues

• Connection refused: Ensure the server is running and the port is accessible
• Model loading errors: Verify model paths and permissions
• Memory issues: Try using a smaller model or enabling GPU acceleration

For more detailed information about the server implementation and advanced usage, visit the official documentation at PaddleOCR GitHub repository.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "paddleocr" '{"command":"python","args":["-m","paddleocr.mcp_server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "paddleocr": {
            "command": "python",
            "args": [
                "-m",
                "paddleocr.mcp_server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "paddleocr": {
            "command": "python",
            "args": [
                "-m",
                "paddleocr.mcp_server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect