Skip to main content
Welcome to Karada! This guide will walk you through the core flow of the platform: creating a project and transforming a standard REST API into an AI-ready Model Context Protocol (MCP) server.

​
Prerequisites

Before you begin, ensure you have:
  1. Created an account on Karada.ai.
  2. A valid OpenAPI or Swagger URL (e.g., https://api.example.com/openapi.json). If you don’t have one, you can use a public API like the Petstore API.

​
Step 1: Create a Workspace and Project

A project in Karada is the top-level container for all your deployments, integrations, and usage tracking.
  1. Navigate to your Dashboard.
  2. If you haven’t already, create a new Team Workspace.
  3. Click the prominent Create Project button in the top right corner.
  4. Select the Auto-MCP template from the list of available providers.
  5. Give your project a descriptive name (e.g., Petstore AI Agent).

​
Step 2: Configure Auto-MCP

Karada’s most powerful feature is Auto-MCP, which turns any API into AI-ready tools.
1

Select Specification Type

Choose between OpenAPI or Swagger depending on the format of your API specification. Karada supports both widely-used standards.
2

Provide the API URL or File

Paste the URL pointing to your .json or .yaml specification file. Alternatively, you can upload the file directly from your local machine.
3

Review the Detected Tools

Karada will immediately parse the specification. You can review the list of detected endpoints, required parameters, and descriptions. These will become the exact tools available to your AI assistant.

​
Step 3: Generate and Deploy

Once you are satisfied with the detected tools:
  1. Click the Generate Server button.
  2. In a few seconds, Karada will compile a fully-functioning TypeScript server.
  3. You can now choose to:
    • Download as ZIP: Run the server locally on your machine.
    • Deploy to Karada: Host the server instantly on our scalable infrastructure.

​
Running Locally (Downloaded ZIP)

If you chose to download the server, follow these steps to run it locally: 
# Unzip the downloaded folder
unzip karada-mcp-server.zip
cd karada-mcp-server

# Install dependencies
npm install

# Start the generated MCP server
npm start

​
Next Steps

Now that you have your MCP server running, you can connect it to AI clients like the Claude Desktop App or Cursor IDE. 👉 Learn more about configuring AI Clients in our Auto-MCP Deep Dive