Skip to main content
Glama
Krayin5 Automated Tests MCP Server

Krayin5 Automated Tests MCP Server

by lucascortazz

Krayin5 Automated Tests MCP Server

A Model Context Protocol (MCP) server that connects to and manages the parent Krayin5 automated testing infrastructure.

Overview

This MCP server provides a bridge to the parent krayin5-automated-tests project, offering tools for:

  • Real Test Execution: Run actual Cucumber.js + Playwright tests

  • Live Status Monitoring: Check current test status and reports

  • Feature Discovery: Browse actual .feature files and test scenarios

  • Coverage Analysis: Analyze test reports and coverage data

Related MCP server: tuxedo-qa

Connection to Parent Project

This MCP server is connected to: ../krayin5-automated-tests

Parent Project Structure:

  • Framework: Cucumber.js + Playwright + TypeScript

  • Features: Authentication, Contact Management, Organization Management

  • Test Types: Smoke, Contact, Organization, Auth, Headless

  • Reports: JSON reports generated in reports/ directory

  • Screenshots: Debug screenshots saved in screenshots/ directory

Features

Available Tools

  1. get_test_status - Get real-time status of the parent test project

  2. run_test_suite - Execute actual test suites from parent project

  3. get_test_coverage - Analyze actual test reports and coverage

  4. list_krayin_test_cases - Browse real feature files and available test suites

Real Test Suites Available

  • all: Run all tests (npm test)

  • smoke: Run smoke tests (npm run test:smoke)

  • contacts: Run contact management tests (npm run test:contacts)

  • organization: Run organization tests (npm run test:organization)

  • auth: Run authentication tests (npm run test:auth)

  • headless: Run tests in headless mode (npm run test:headless)

Installation

  1. Clone this repository

  2. Install dependencies:

    npm install
  3. Build the project:

    npm run build

Usage

With Claude Desktop

Add this server to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "krayin5-automated-tests": {
      "command": "node",
      "args": ["/Users/lucascortazzo/code/mcp-krayin5-automated-tests/build/index.js"]
    }
  }
}

Direct Usage

Run the server directly:

npm start

Development

  • Build: npm run build

  • Development: npm run dev (builds and runs)

  • Start: npm start (runs pre-built version)

MCP Integration

This server implements the Model Context Protocol specification and can be used with any MCP-compatible client, including:

  • Claude Desktop

  • VS Code with MCP extensions

  • Custom MCP clients

Project Structure

├── src/
│   └── index.ts          # Main MCP server implementation
├── build/                # Compiled JavaScript (generated)
├── .github/
│   └── copilot-instructions.md
├── .vscode/
│   └── mcp.json         # VS Code MCP configuration
├── package.json
├── tsconfig.json
└── README.md

Contributing

  1. Make changes to TypeScript source files in src/

  2. Build the project with npm run build

  3. Test with your MCP client

  4. Ensure all TypeScript compilation passes without errors

License

ISC

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    • Comeet MCP server for ChatGPT, Claude and any AI agent: list candidates, change candidate status, reject candidate with reason, decide Go/No-go step, invite candidate to self-schedule, add comment, tag candidate and add candidate in your own Comeet account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Comeet yourself; Cotlet does not store your password and you need no Comeet API key. About the official Comeet API: Comeet, now Spark Hire Recruit, has a Recruiting API, but Comeet grants access at its sole discretion under partner terms (checked 22 Oct 2026). Its beta MCP connection for ChatGPT and Claude searches live candidate, position and pipeline data and lists nothing that changes a record. Setup and FAQ: https://cotlet.dev/integrations/comeet-api-mcp-server

      https://cotlet.dev/mcp/v1/comeet
    • Productboard MCP server for ChatGPT, Claude and any AI agent: search features, read feedback, add feedback, link feedback to a feature, mark feedback processed, update feature status and list objectives in your own Productboard account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Productboard yourself; Cotlet does not store your password and you need no Productboard API key. About the official Productboard API: Productboard has a full REST API v2 for notes, entities, teams, members, webhooks and analytics, and a beta MCP server at mcp.productboard.com that works on specs (checked 22 Oct 2026). API tokens need a workspace admin on the Pro plan or higher, and the API reference lists no endpoints for boards. Setup and FAQ: https://cotlet.dev/integrations/productboard-api-mcp-server

    • WorkRamp MCP server for ChatGPT, Claude and any AI agent: list assignments, remind learners, assign training, change due date, unassign learner, get learner transcript, set reminder cadence and run automation in your own WorkRamp account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to WorkRamp yourself; Cotlet does not store your password and you need no WorkRamp API key. About the official WorkRamp API: WorkRamp has a REST API, but it is private: you ask support@workramp.com for access, it needs an enterprise account, and tokens come only from Admin users (checked 22 Oct 2026). WorkRamp's own MCP server is announced in its June 2026 product roundup and described as read and search of guides and assignments, with no write tools. Setup and FAQ: https://cotlet.dev/integrations/workramp-api-mcp-server

    • Plausible MCP server for ChatGPT, Claude and any AI agent: list sites, get site stats, get top pages, get traffic sources, create site, add goal, create shared link and invite guest in your own Plausible account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Plausible yourself; Cotlet does not store your password and you need no Plausible API key. About the official Plausible API: Plausible has an official API, but a limited one (checked 22 Oct 2026). The Stats API only reads data and needs the Business plan, the Sites API that creates sites, goals and shared links is Enterprise only, and there is no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/plausible-api-mcp-server

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to create, run, autocorrect, and monitor Playwright tests for your app with a local dashboard, credential vault, and public status page.
      16
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to execute mobile automation tests using Cucumber.js, including device management, test scenarios, and APK uploads.
      ISC
    • A
      license
      Not graded
      quality
      C
      maintenance
      Converts requirements into traceable, CI-ready Playwright BDD tests connected to business rules, with support for Gherkin generation, rule mapping, and automated test pipelines.
      12 npm
      MIT