You’ll need a Databrain account and Node.js 18+ installed. The setup takes about 2 minutes.
Prerequisites
- Node.js 18+ — check with
node --version - A Databrain account — sign up here if you don’t have one
- An AI client — Cursor, Claude Desktop, Claude Code, or Windsurf
Get Your Service Token
- Log in to Databrain
- Go to Settings → Service Tokens
- Create a new token and copy it
Add to Your AI Client
Add the MCP server configuration to your client. Pick your client below:For detailed per-client instructions including restart steps and self-hosted configuration, see the Client Setup Guide.
- Cursor
- Claude Desktop
- Claude Code
- Windsurf
- Other
Add to
.cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):Verify the Connection
Open your AI assistant and ask:
“List my Databrain datasources”If everything is configured correctly, you’ll see your connected datasources listed. This confirms the MCP server is running and your service token is valid.
Try It Out
Now try a real task:
“Set up a Databrain embed for my dashboard”The assistant walks you through each step interactively — picking your data app, selecting a workspace and dashboard, creating the embed, and generating the frontend code. You approve each step as it goes.Other things to try:
“What was total revenue last month?”
“Brand my embed to match our company colors”
That’s it. The assistant handles the Databrain API so you can focus on building.
Next Steps
Workflows
Step-by-step guides for common tasks
Client Setup
Detailed configuration per client
Tools Reference
All 24 available tools

