Kayzen

Provides access to Kayzen Analytics data through an MCP interface with authenticated report retrieval and analysis.

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "springwq-kayzen-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@feedmob-ai/kayzen-mcp"
      ],
      "env": {
        "KAYZEN_BASE_URL": "https://api.kayzen.io/v1",
        "KAYZEN_PASSWORD": "YOUR_PASSWORD",
        "KAYZEN_USERNAME": "YOUR_USERNAME",
        "KAYZEN_BASIC_AUTH": "YOUR_BASIC_AUTH_TOKEN"
      }
    }
  }
}

You can run and use the Kayzen Analytics MCP Server to securely access and analyze Kayzen advertising campaign data through a standardized interface. This server handles authentication, retrieves analytics reports, and analyzes results, enabling you to build AI-assisted insights into your Kayzen data.

How to use

To use the Kayzen MCP Server with an MCP client, start the server locally and connect via the provided command-line method. Once running, you can list available reports, fetch specific report results for given date ranges, and run analysis on those results to extract performance insights and optimization opportunities.

How to install

Prerequisites: you need Node.js (v16 or higher) and npm (v7 or higher). You also require Kayzen API credentials to authenticate with the Kayzen service.

Step-by-step setup and run flow:

# Install the MCP server package
npm install @feedmob-ai/kayzen-mcp

# Create a configuration file for your environment (example .env)
# (replace placeholders with your actual credentials)
KAYZEN_USERNAME=your_username
KAYZEN_PASSWORD=your_password
KAYZEN_BASIC_AUTH=your_basic_auth_token
KAYZEN_BASE_URL=https://api.kayzen.io/v1

# Build the project (if required by your setup)
npm run build

# Start the server
npm start

# Optional development mode with hot-reload
npm run dev

Additional setup tips

If you prefer to run the MCP server with a one-off invocation via npx for quick testing, you can use the included npm/npx example configuration to launch the server and pass the required environment variables. This approach is suitable for quick experiments or ephemeral runs.

# Example MCP startup using npx (as shown in usage examples)
npx -y @feedmob-ai/kayzen-mcp

Available tools

list_reports

Retrieves the list of available Kayzen analytics reports with identifiers and metadata.

get_report_results

Fetches the results for a specific report, optionally bounded by start and end dates.

analyze_report_results

Analyzes the results of a report to provide performance insights, trends, and optimization recommendations.

Built by

VeilStrat

AI signals for GTM teams