Skip to main content

​
Prerequisites

​
Choose Your Approach

SDK

TypeScript/Node.js and Python SDKs for type-safe development

REST API

Language-agnostic HTTP API for any platform

CLI

Manage workflows from the terminal and CI/CD pipelines

MCP Server

Use Kadoa from ChatGPT, Claude, Cursor, and other AI assistants

​
Installation

​
SDK

npm install @kadoa/node-sdk
You can view the Kadoa SDK source code on GitHub.

​
CLI

npm install -g @kadoa/cli
Enable tab completions for workflow IDs, subcommands, and flags: 
# Add to ~/.zshrc
eval "$(kadoa completion zsh)"
Zsh shows workflow names inline: kadoa get <TAB> displays abc123 -- My Workflow.

​
MCP Server

The remote MCP server at https://mcp.kadoa.com/mcp requires no local install or API key — connect from your MCP client and sign in with your Kadoa account via OAuth. See MCP Server setup for per-client instructions. For local use via stdio: 
npx -y @kadoa/mcp

​
Quick Start

import { KadoaClient } from '@kadoa/node-sdk';

const client = new KadoaClient({
  apiKey: 'YOUR_API_KEY'
});

const result = await client.extraction.run({
  urls: ["https://sandbox.kadoa.com/ecommerce"],
  name: "My First Extraction",
  limit: 10,
});

console.log(result.data);
That’s it! With the SDK, data is automatically extracted. With the API, you define the schema and then retrieve your structured data.

​
Define What to Extract

For more control, specify exactly what fields you want: 
const workflow = await client
  .extract({
    urls: ["https://sandbox.kadoa.com/ecommerce"],
    name: "Product Monitor",
    extraction: (builder) =>
      builder
        .entity("Product")
        .field("name", "Product name", "STRING", {
          example: "MacBook Pro",
        })
        .field("price", "Price in USD", "MONEY")
        .field("inStock", "Is available", "BOOLEAN"),
  })
  .create();

const result = await workflow.run({ limit: 10 });
const response = await result.fetchData({});
console.log(response.data);

​
Next Steps