Skip to main content

​
DumplingAI API Reference

Welcome to the DumplingAI API reference. This documentation provides detailed information about all available endpoints, request parameters, response formats, and example code.

​
Authentication

All API requests require authentication using an API key. To use the API, you need to include your API key in the Authorization header of your requests. 
Authorization: Bearer YOUR_API_KEY
If you don’t have an API key yet, sign in to the DumplingAI dashboard and generate one from the API Keys section.

​
Base URL

All API endpoints should be accessed through our base URL: 
https://app.dumplingai.com

​
Response Format

All responses are returned in JSON format. Successful responses will have a 2xx status code, while errors will return appropriate 4xx or 5xx status codes with error details in the response body.

​
Success Response Example

{
  "data": { ... },
  "status": "success"
}

​
Error Response Example

{
  "error": {
    "code": "invalid_request",
    "message": "The request was invalid. Please check your parameters."
  },
  "status": "error"
}

​
Rate Limiting

Rate limiting is applied based on your subscription plan. Rate limits are enforced based on your account’s credit allocation and usage patterns. If you exceed these limits, you’ll receive a 429 Too Many Requests error response.

​
Versioning

The current API version is v1. We recommend explicitly specifying the API version in your requests to ensure compatibility as we evolve the API.

​
MCP Server Integration

For AI assistants and workflow automation tools, DumplingAI offers a Model Context Protocol (MCP) server. This provides a standardized way to access all DumplingAI tools directly from compatible clients like Cursor, Windsurf, n8n, and Claude Desktop.

​
Benefits of MCP

  • No code integration: AI assistants can use DumplingAI tools without manual API integration
  • Simplified workflows: Build automation with natural language instead of code
  • Direct tool access: Access all 53 DumplingAI tools through your AI assistant

​
Getting Started with MCP

Connect to the DumplingAI MCP server: Remote Server (Recommended):
  • Endpoint: https://app.dumplingai.com/api/mcp
  • Authentication: Bearer token with your API key
  • Supports: Cursor, Windsurf, n8n
Local Server:
  • Package: mcp-server-dumplingai (npm)
  • Supports: Claude Desktop and stdio-based clients
  • GitHub Repository
See the MCP Server Integration Guide for detailed setup instructions and examples.

​
API Endpoints

Explore all available API endpoints in the sidebar navigation.
⌘I