What is the Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs, enabling them to interact with external data sources and tools.

What does the Triplewhale MCP Server do?

It connects your Triplewhale marketing data with Large Language Models (LLMs) like Claude, allowing you to query your marketing data using natural language.

What are the requirements for using the Triplewhale MCP Server?

You need Node.js (>= v18.0.0), Claude Desktop (or another MCP Client), and a Triplewhale API key.

How do I install the Triplewhale MCP Server?

You can install it automatically via Smithery or manually using npm.

How do I get a Triplewhale API key?

You can generate one through the Triplewhale console.

What kind of questions can I ask once it’s set up?

You can ask questions like “What was my net profit last month?” or “Give me ads ROAS over the last 7 days and break it out by attribution model?”

Do I need to restart Claude after installing?

Yes, you need to restart Claude Desktop after installing the Triplewhale MCP Server for the integration to take effect.

Can I use this with other MCP clients besides Claude?

Yes, any MCP-compatible client can be used, but Claude Desktop is specifically mentioned in the documentation.

Is this a secure way to access my Triplewhale data?

Yes, the Triplewhale API key ensures secure access to your data.

Where can I find more information about UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department.