Skip to main content
Glama
Kayzen Analytics MCP Server

Kayzen Analytics MCP Server

by springwq

Kayzen Analytics MCP Server

A Model Context Protocol (MCP) server implementation for interacting with Kayzen Analytics API. This package enables AI models to access and analyze Kayzen advertising campaign data through a standardized interface.

Features

  • Automated Authentication: Built-in token management with automatic refresh mechanism

  • Report Management: Easy access to Kayzen analytics reports

  • Error Handling: Comprehensive error handling for API interactions

  • TypeScript Support: Full TypeScript implementation with type definitions

  • Environment Based Configuration: Simple setup using environment variables

Related MCP server: Amazon Ads API MCP SDK

Installation

npm install @feedmob-ai/kayzen-mcp

Configuration

Create a .env file with your Kayzen credentials:

KAYZEN_USERNAME=your_username
KAYZEN_PASSWORD=your_password
KAYZEN_BASIC_AUTH=your_basic_auth_token
KAYZEN_BASE_URL=https://api.kayzen.io/v1  # Optional, defaults to this value

Usage

Basic Setup

import { KayzenMCPServer } from '@feedmob-ai/kayzen-mcp';

const server = new KayzenMCPServer();
server.start();

Available Tools

1. list_reports

Lists all available reports from Kayzen Analytics.

  • Inputs: None

  • Returns: Array of report objects containing:

    • id: Report identifier

    • name: Report name

    • type: Report type

const reports = await server.tools.list_reports();

2. get_report_results

Retrieves results for a specific report.

  • Inputs:

    • report_id (string, required): ID of the report to fetch

    • start_date (string, optional): Start date in YYYY-MM-DD format

    • end_date (string, optional): End date in YYYY-MM-DD format

  • Returns: Report data and metadata

const results = await server.tools.get_report_results({
  report_id: 'report_id',
  start_date: '2024-01-01',  // optional
  end_date: '2024-01-31'     // optional
});

3. analyze_report_results (Prompt)

Analyzes report results and provides insights.

  • Inputs:

    • report_id (string): ID of the report to analyze

  • Analysis includes:

    • Performance metrics

    • Key trends

    • Areas for optimization

    • Unusual patterns or anomalies

Setup

Usage with Claude Desktop

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

NPX

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@feedmob-ai/kayzen-mcp"
      ],
      "env": {
        "KAYZEN_USERNAME": "username",
        "KAYZEN_PASSWORD": "pasword",
        "KAYZEN_BASIC_AUTH": "auth token"
      }
    }
  }
}

Development

Prerequisites

  • Node.js (v16 or higher)

  • npm (v7 or higher)

  • Kayzen API credentials

Scripts

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm start

# Development mode with hot-reload
npm run dev

Project Structure

kayzen-mcp/
├── src/
│   ├── server.ts        # MCP server implementation
│   └── kayzen-client.ts # Kayzen API client
├── dist/               # Compiled JavaScript
└── package.json       # Project configuration

Dependencies

Main dependencies:

  • @modelcontextprotocol/sdk: ^1.7.0

  • axios: ^1.8.3

  • dotenv: ^16.4.7

  • zod: ^3.24.2

Error Handling

The server handles various error scenarios:

  • Authentication failures

  • Invalid API requests

  • Network issues

  • Token expiration and refresh

  • Invalid parameters

License

MIT License

Author

FeedMob

Available Tools

2 tools
get_report_resultsD

Inputs: report_id (required), end_date, start_date.

list_reportsD

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    D1.8/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: 'get_report_results' appears to retrieve specific report data, while 'list_reports' enumerates available reports. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on whether it needs to list reports or fetch results from a particular report.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun naming pattern ('get_report_results' and 'list_reports'), using snake_case throughout. The verbs 'get' and 'list' are standard and predictable, making the tool names easy to understand and use without confusion.

    Tool Count2/5

    With only two tools, the server feels under-scoped for an analytics domain, which typically involves operations like creating, updating, filtering, or deleting reports. This minimal set may force agents to work around gaps, such as being unable to generate new reports or modify existing ones, limiting functionality.

    Completeness2/5

    The tool surface is severely incomplete for analytics: it allows listing and retrieving reports but lacks essential operations like creating, updating, deleting, or filtering reports. This creates significant gaps that will likely cause agent failures when trying to perform common analytics tasks beyond basic read-only access.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered advertising applications by providing MCP-compliant tools to interact with Amazon Ads API for campaign management, reporting, and optimization.
      3
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to manage, report, and analyze Google Ads campaigns securely with encrypted multi-client support, real-time API integrations, and audit trail logging.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to query campaign performance, metrics, audiences, and geography, and to analyze budgets, wasted spend, and account health through natural language.
      1
      MIT