Lightweight Model Context Protocol (MCP) server for PaddleOCR integration.

Created 11 months ago

development location documentation public MCP

What is Lightweight Model Context Protocol (MCP) server for PaddleOCR integration.?

This project provides a lightweight Model Context Protocol (MCP) server designed to integrate PaddleOCR capabilities into various LLM applications. It supports OCR and PP-StructureV3 functionalities, allowing for text detection, recognition, and layout extraction from images and PDF files.

Documentation

MCP Server for Paddle Billing

Paddle Billing is the developer-first merchant of record. We take care of payments, tax, subscriptions, and metrics with one unified API that does it all.

This is a Model Context Protocol (MCP) server that provides tools for interacting with the Paddle API.

Important: This MCP server works with Paddle Billing. It does not support Paddle Classic. To work with Paddle Classic, see: Paddle Classic API reference

Features

List products in your Paddle catalog
Create new products
List prices for products
Create new prices for products
List customers
List transactions
List subscriptions
Create custom reports for financial analysis

Installation

To use the MCP server, you'll need an API key. You can create and manage API keys in Paddle > Developer tools > Authentication:

Sandbox: https://sandbox-vendors.paddle.com/authentication-v2
Live: https://vendors.paddle.com/authentication-v2

To run the server in a client like Claude Desktop, Cursor or Windsurf, add the following to your MCP config:

{
  "mcpServers": {
    "paddle": {
      "command": "npx",
      "args": ["-y", "@paddle/paddle-mcp", "--api-key=PADDLE_API_KEY", "--environment=(sandbox|production)"]
    }
  }
}

Replace PADDLE_API_KEY with your API key, and pass the correct value as environment.

For detailed setup guides, see:

Development

Install dependencies:
```
pnpm install
```
Build the server:
```
pnpm build
```

Update client to use the local build:

{
  "mcpServers": {
    "paddle": {
      "command": "node",
      "args": ["path/to/paddle-mcp-server/build/index.js"],
      "env": {
        "PADDLE_API_KEY": "your_api_key",
        "PADDLE_ENVIRONMENT": "sandbox"
      }
    }
  }
}

Debugging

To debug the MCP server, you can use the MCP Inspector tool:

Run the server with the inspector:
```
pnpm inspector
```
Open the provided URL in your browser to view and debug the MCP requests and responses.
Include the --api-key and --environment arguments.

Learn more

Server Config

{
  "mcpServers": {
    "lightweight-model-context-protocol-(mcp)-server-for-paddleocr-integration.-server": {
      "command": "npx",
      "args": [
        "lightweight-model-context-protocol-(mcp)-server-for-paddleocr-integration."
      ]
    }
  }
}

Links & Status

Repository: paddlepaddle.github.io

Hosted: Yes

Global: Yes

Official: Yes

Project Info

Hosted Featured

Created At: Aug 07, 2025

Updated At: Aug 07, 2025

Author: PaddleOCR PMC

Category: OCR, Document Processing

License: Apache 2.0

Tags:

development location documentation