Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Enables test execution and management through MCP clients, allowing retrieval of projects, listing tests, executing tests with browser selection, and monitoring results.

README.md

MCP DevOps Test Server

A Model Context Protocol (MCP) server implementation for DevOps Test, enabling test execution and management through standardized MCP clients.

Features

  • Retrieve projects from the Test system
  • List tests from specific projects with optional filtering
  • Execute tests in projects with browser selection
  • Monitor test execution results and status
  • Download and analyze test logs from execution archives

Warranties

This MCP server is provided "as is" without any warranties. It is designed to work with the DevOps Test system and may require specific configurations to function correctly. Users are responsible for ensuring compatibility with their Test instance. This server provides test execution functionality, the author is not liable for any issues arising from test execution or system interactions.

Example Use Cases

1. Automated Test Execution Pipeline

Scenario: You're a QA engineer who needs to execute a suite of tests across different projects and monitor their results.

Steps:

  1. "Get me all available projects in the Test system"
  2. "Show me all tests in the 'WebApp Testing' project"
  3. "Execute the 'LoginFunctionalityTest' in the WebApp Testing project using Chrome browser"
  4. "Check the results of the test execution and get the detailed report"
  5. "Download the test logs for further analysis"

Benefits: Streamline test execution and monitoring without manual interface interaction.

2. Cross-Browser Test Validation

Scenario: You need to validate functionality across different browsers for a critical release.

Steps:

  1. "List all UI tests in the 'E-commerce Platform' project"
  2. "Execute the 'CheckoutProcessTest' using Edge browser"
  3. "Monitor the test results and wait for completion"
  4. "Execute the same test using Chrome browser for comparison"
  5. "Download logs from both executions to compare results"

Benefits: Efficiently coordinate cross-browser testing and result comparison.

3. Continuous Integration Test Monitoring

Scenario: You're monitoring test results as part of a CI/CD pipeline and need real-time status updates.

Steps:

  1. "Get all projects and identify the relevant test project"
  2. "List tests of type 'EXT_TEST_SUITE' for automated test suites"
  3. "Execute critical test suites for the latest build"
  4. "Continuously monitor test execution status until completion"
  5. "Retrieve comprehensive test results and logs for CI reporting"

Benefits: Integrate test execution monitoring into automated workflows and CI/CD pipelines.

  1. "Create a dependent task 'Integrate user profile API' in the 'Frontend' component"
  2. "Check work items assigned to backend team members to see their current workload"

Benefits: Coordinate cross-functional work and ensure proper dependency tracking.

Configuration

The server requires configuration for authentication and connection to your Test instance. You can provide configuration in several ways:

Manual Setup

Create a .env file in the project root and add your configuration values:

# Copy the example below and fill in your actual values
TEST_ACCESS_TOKEN=your_base64_encoded_token_here
TEST_SERVER_URL=https://your-test-server.com/test
TEST_TEAMSPACE_ID=your-teamspace-id-here
TEST_INSECURE_TLS=false

Option 1: Environment Variables

Set the following environment variables:

export TEST_ACCESS_TOKEN="your_base64_encoded_token_here"
export TEST_SERVER_URL="https://your-test-server.com/test"
export TEST_TEAMSPACE_ID="your-teamspace-id-here"
export TEST_INSECURE_TLS="false"

Option 2: Command Line Arguments

Pass configuration as command line arguments:

node src/lib/server.js --token "your_token" --server-url "https://your-server.com/test" --teamspace-id "your-teamspace-id"

If your Test server uses a self-signed or otherwise untrusted certificate, add --insecure-tls to disable certificate validation for this process only:

node src/lib/server.js --token "your_token" --server-url "https://your-server.com/test" --teamspace-id "your-teamspace-id" --insecure-tls

Option 3: Environment File

Create a .env file in the project root with your values:

# Create .env file with your actual configuration values
TEST_ACCESS_TOKEN=your_base64_encoded_token_here
TEST_SERVER_URL=https://your-test-server.com/test
TEST_TEAMSPACE_ID=your-teamspace-id-here
TEST_INSECURE_TLS=false

Configuration Parameters

| Parameter | Environment Variable | Command Line Argument | Required | Default | Description | |-----------|---------------------|----------------------|----------|---------|-------------| | Access Token | TEST_ACCESS_TOKEN | --token | ✅ Yes | None | Base64 encoded personal access token for authentication | | Server URL | TEST_SERVER_URL | --server-url | ✅ Yes | None | URL to your Test server instance | | Teamspace ID | TEST_TEAMSPACE_ID | --teamspace-id | ✅ Yes | None | Your Test teamspace identifier | | Insecure TLS | TEST_INSECURE_TLS | --insecure-tls | No | false | Disable TLS certificate validation for self-signed or untrusted server certificates |

Note: The server now uses a simplified authentication system that calls the /rest/tokens endpoint instead of Keycloak. This requires only your personal access token for authentication. Security note: Only enable insecure TLS for trusted internal environments. It disables HTTPS certificate verification for the MCP server process.

Installation

Prerequisites

  • Node.js >= 18.0.0
  • npm or yarn package manager

Option 1: Direct NPX Usage (Recommended)

You can run the MCP server directly without installation:

npx @securedevops/mcp-devops-test --token "your_token" --server-url "https://your-server.com/test" --teamspace-id "your-teamspace-id"

For self-signed certificates:

npx @securedevops/mcp-devops-test --token "your_token" --server-url "https://your-server.com/test" --teamspace-id "your-teamspace-id" --insecure-tls

Option 2: Global Installation

npm install -g @securedevops/mcp-devops-test
mcp-devops-test --token "your_token" --server-url "https://your-server.com/test" --teamspace-id "your-teamspace-id"

Option 3: Local Development

For development or customization:

# Clone the repository
git clone https://github.com/securedevops/mcp-devops-test.git
cd mcp-devops-test

# Install dependencies
npm install

# Create configuration file (see Configuration section below)
# Create .env file with your configuration values

# Start the MCP server
npm start

Use with Claude Desktop

Option 1: NPX (Recommended)

Add the following to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "devops-test": {
      "command": "npx",
      "args": [
        "@securedevops/mcp-devops-test",
        "--token", "your_token_here",
        "--server-url", "https://your-server.com/test",
        "--teamspace-id", "your_teamspace_id"
      ]
    }
  }
}

Option 2: Environment Variables with NPX

{
  "mcpServers": {
    "devops-test": {
      "command": "npx",
      "args": ["@securedevops/mcp-devops-test"],
      "env": {
        "TEST_ACCESS_TOKEN": "your_token_here",
        "TEST_SERVER_URL": "https://your-server.com/test",
        "TEST_TEAMSPACE_ID": "your_teamspace_id",
        "TEST_INSECURE_TLS": "false"
      }
    }
  }
}

Option 3: Local Installation

Add the following to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "devops-test": {
      "command": "node",
      "args": ["/path/to/mcp-devops-test/src/lib/server.js"],
      "env": {
        "TEST_ACCESS_TOKEN": "your_token_here",
        "TEST_SERVER_URL": "https://your-server.com/test",
        "TEST_TEAMSPACE_ID": "your_teamspace_id",
        "TEST_INSECURE_TLS": "false"
      }
    }
  }
}

Or with command line arguments:

{
  "mcpServers": {
    "devops-test": {
      "command": "node",
      "args": [
        "/path/to/mcp-devops-test/src/lib/server.js",
        "--token", "your_token_here",
        "--server-url", "https://your-server.com/test",
        "--teamspace-id", "your_teamspace_id",
        "--insecure-tls"
      ]
    }
  }
}

Usage

The MCP DevOps Test server provides the following tools for interacting with DevOps Test:

Available Tools

1. get_projects

Purpose: Retrieves all projects from the Test system Parameters: None Usage: Use this to get a list of all available projects in your Test instance. This is typically the first step to understand what projects you can work with for test execution.

2. list_tests

Purpose: Retrieves tests from a specific project with optional test type filtering Parameters:

  • projectId (string): The ID of the project to retrieve tests from
  • testType (string, optional): Optional test type filter (e.g., EXT_TEST_SUITE, EXT_TEST_SCPT, EXT_TEST_LOADP, EXT_TEST_STUB, etc.)
  • branch (string, optional): Branch to use for retrieving tests (default: main)

Usage: Once you have a project ID, use this to see all tests within that project. You can filter by specific test types if needed.

3. execute_test

Purpose: Execute a test in a specific project by test name Parameters:

  • projectId (string): The ID of the project containing the test
  • testName (string): The name of the test to execute
  • browserName (string, optional): Browser to use for execution (default: edge)
  • revision (string, optional): Revision to use (default: main)

Usage: Execute a specific test within a project. Tests typically take 60-180 seconds to complete. Important: After execution, wait at least 60 seconds before checking results, then use progressive back-off for status checks.

4. get_test_results

Purpose: Get comprehensive test execution results and report data Parameters:

  • projectId (string): The ID of the project containing the test
  • resultId (string): The result ID from the test execution
  • executionId (string, optional): Optional execution ID for additional context

Usage: Monitor test execution progress and retrieve detailed results. Use progressive polling if status is RUNNING: 30s → 45s → 60s → 90s between checks.

5. get_test_log_results

Purpose: Download and analyze test log results from the zip archive Parameters:

  • projectId (string): The ID of the project containing the test
  • downloadId (string): The download ID for the result archive (from test execution results)

Usage: Download detailed test logs and artifacts from completed test executions for further analysis and debugging.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Browser & Scraping servers.