Skip to main content

Overview

This guide will help you connect your AI assistant to Danube and execute your first tool. We’ll use Cursor as an example, but the same approach works for any MCP client. The Danube MCP Server URL is https://mcp.danubeai.com/mcp.

Step 1: Get Your API Key

1

Sign Up or Log In

Go to danubeai.com and create an account or sign in.
2

Open API Keys

Click API Keys in the dashboard sidebar, or go straight to danubeai.com/dashboard/api-keys.
3

Create a New Key

Click Create API Key, give it a name like “My MCP Client”, and copy the key.

Step 2: Choose Your Integration

Connect your AI assistant to Danube via the Model Context Protocol:

Claude Desktop

Anthropic’s desktop app

Claude Code CLI

Terminal AI assistant

Codex

OpenAI’s desktop app

Codex CLI

OpenAI’s terminal agent

Cursor

AI-powered code editor

Windsurf

Codeium’s code editor

Hermes Agent

Nous Research’s open-source agent

Other

Any MCP client

Step 3: Make Your First Tool Call

MCP Prompt: “What services are available on Danube?”CLI: danube services listSDK: client.services.list(limit=5)
MCP Prompt: “Search for tools related to news”CLI: danube search "news"SDK: client.tools.search("news")
MCP Prompt: “Get the top 5 stories from Hacker News”CLI: danube execute "Hacker News - Get Top Stories With Content"SDK: client.tools.execute(tool_name="Hacker News - Get Top Stories With Content")

Troubleshooting

  • Make sure you completely restarted your MCP client
  • Check that your API key is correct
  • Verify the JSON/TOML syntax in your config file
  • Your API key may be invalid or expired
  • For MCP clients, ensure the header is named exactly danube-api-key (lowercase)
  • Generate a new API key from the dashboard
  • Check your internet connection
  • Verify the server is reachable: curl https://mcp.danubeai.com/health

Next Steps

MCP Clients

Detailed setup for every MCP client

Python SDK

Full SDK reference and examples

API Reference

REST API documentation