Triple Whale MCP server

Integrates with Triple Whale's API to enable querying and analysis of e-commerce performance metrics for sales reporting and marketing strategy optimization.
Back to servers
Provider
Triple Whale
Release date
Feb 27, 2025
Language
TypeScript
Package
Stats
515 downloads
1 star

This MCP server allows you to interact with Triplewhale using natural language through Claude Desktop or any MCP client. The Model Context Protocol (MCP) creates a standardized way for large language models to communicate with external systems, enabling you to query your Triplewhale data with simple questions about revenue, profits, ads performance, and more.

Installation Options

Quick Installation via Smithery

The easiest way to install the Triplewhale MCP Server for Claude Desktop is through Smithery:

npx -y @smithery/cli install triplewhale --client claude

Manual Installation

To install the server locally:

npx -y @triplewhale/mcp-server-triplewhale init $TRIPLEWHALE_API_KEY

Replace $TRIPLEWHALE_API_KEY with your actual Triplewhale API key.

Requirements

Before installation, ensure you have:

  • Node.js ≥ v18.0.0
  • Claude Desktop installed
  • A Triplewhale API key (generate one through the Triplewhale console)

Getting Started

After installation:

  1. Restart Claude Desktop to load the new MCP server
  2. Start asking questions about your Triplewhale data

Example Queries

You can ask questions like:

  • "Was my net profit positive last month?"
  • "Rank countries by order revenue and new users for the last quarter."
  • "Give me ads ROAS over the last 7 days and break it out by attribution model?"
  • "What's my meta spend in the last 7 days?"

Supported Tools

The MCP server currently supports:

  • moby (Triplewhale's data analysis tool)

Troubleshooting

If you encounter issues:

  • Verify your Triplewhale API key is valid
  • Ensure Claude Desktop has been restarted after installation
  • Check that you're meeting the Node.js version requirements

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later