MCP Test Runner
mcp-test-runner is an MCP server that lets your AI client (Claude / Cursor / Codex / Gemini) drive your entire QA loop end-to-end: * Run tests across pytest / Jest / Cypress / Go / Maestro — single MCP surface, one env var to switch * Analyze a URL (
What is MCP Test Runner?
MCP Test Runner is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp-test-runner is an mcp server that lets your ai client (claude / cursor / codex / gemini) drive your entire qa loop end-to-end: * run tests across pytest / jest / cypress / go / maestro — single mc...
mcp-test-runner is an MCP server that lets your AI client (Claude / Cursor / Codex / Gemini) drive your entire QA loop end-to-end: * Run tests across pytest / Jest / Cypress / Go / Maestro — single MCP surface, one env var to switch * Analyze a URL (
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- mcp-test-runner is an MCP server that lets your AI client (C
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mk-qa-masterConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Test Runner
mk-qa-master (mcp-test-runner) is an MCP server that gives AI assistants end-to-end control over a QA testing loop spanning pytest, Jest, Cypress, Go tests, Maestro mobile flows, Schemathesis OpenAPI fuzzing, Newman/Postman collection replay, and Edge AI RTSP/YOLO scenarios — all through a single MCP surface. It exposes 22 tools covering test execution, failure analysis, smart test generation from page or screen inspection, HTML reporting, and even OWASP API security scanning. QA engineers and AI coding agents use it to run, analyze, generate, and iterate on tests without switching between tools.
Prerequisites
- Python 3.10+ and pip, plus uvx for the zero-install approach
- The test framework matching your project installed: pytest, Jest/Cypress (Node.js), Go toolchain, Maestro CLI, or newman
- For web UI testing with pytest-playwright: run 'playwright install chromium' after pip install
- QA_RUNNER and QA_PROJECT_ROOT environment variables set to select the framework and project path
- An MCP-compatible client such as Claude Desktop, Cursor, or Gemini
Install mk-qa-master
Install via pip for persistent use, or use uvx for a zero-install approach. For playwright support, also install Playwright browsers.
pip install mk-qa-master
# For Playwright:
playwright install chromiumRun the doctor command to verify setup
The built-in doctor command checks that required framework dependencies are available.
mk-qa-master doctorConfigure your MCP client
Add mk-qa-master to your MCP client config. Set QA_RUNNER to your framework (pytest, jest, cypress, go, maestro, schemathesis, newman, or edge) and QA_PROJECT_ROOT to the absolute path of your test project.
{
"mcpServers": {
"mk-qa-master": {
"command": "uvx",
"args": ["mk-qa-master"],
"env": {
"QA_RUNNER": "pytest",
"QA_PROJECT_ROOT": "/absolute/path/to/your-project"
}
}
}
}Restart your MCP client
Restart Claude Desktop or your MCP client so it picks up the new server and environment variables.
Run tests and analyze failures
Ask your AI assistant to run your test suite. The server will execute the tests, capture screenshots and traces on failure, and return structured results.
Generate and iterate on tests
Use the analyze_url or analyze_screen tools to inspect a page or mobile screen, then ask the assistant to generate new tests with concrete selectors based on the live DOM or view hierarchy.
MCP Test Runner Examples
Client configuration
Claude Desktop configuration for mk-qa-master with a Jest project.
{
"mcpServers": {
"mk-qa-master": {
"command": "uvx",
"args": ["mk-qa-master"],
"env": {
"QA_RUNNER": "jest",
"QA_PROJECT_ROOT": "/home/user/my-node-project",
"QA_TIMEOUT_SECONDS": "120"
}
}
}
}Prompts to try
Example prompts once mk-qa-master is connected.
- "Run all tests in my project and show me a summary of failures"
- "Re-run only the failed tests from the last run"
- "Analyze the login page at https://app.example.com and generate pytest-playwright tests for the login flow"
- "Generate an HTML report for the latest test run and show me trend data"
- "Run an API security scan against https://api.example.com/openapi.json"
- "Give me an optimization plan based on the last 5 test runs"Troubleshooting MCP Test Runner
Tests time out and return exit code 124
Increase QA_TIMEOUT_SECONDS in your environment configuration. The default is 600 seconds. For long-running Cypress or Maestro suites, set it to 1200 or higher.
QA_RUNNER is set but the framework binary is not found
Ensure the framework CLI is on the PATH of the process running mk-qa-master. For Jest/Cypress, run 'npm i -D jest' or 'npm i -D cypress' in QA_PROJECT_ROOT. For Maestro, verify 'maestro --version' works in your shell.
API security scan or visual challenge solver is blocked
These features require explicit consent. Set QA_API_SECURITY_CONSENT=true and QA_API_SECURITY_AUTHORIZED_DOMAINS for the security scanner, or QA_VISUAL_CHALLENGE_CONSENT=true for the visual challenge solver.
Frequently Asked Questions about MCP Test Runner
What is MCP Test Runner?
MCP Test Runner is a Model Context Protocol (MCP) server that mcp-test-runner is an mcp server that lets your ai client (claude / cursor / codex / gemini) drive your entire qa loop end-to-end: * run tests across pytest / jest / cypress / go / maestro — single mcp surface, one env var to switch * analyze a url ( It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Test Runner?
Follow the installation instructions on the MCP Test Runner GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Test Runner?
MCP Test Runner works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Test Runner free to use?
Yes, MCP Test Runner is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Test Runner Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Test Runner? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Test Runner in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Test Runner?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.