AI QA Agent MCP
Analyzes Playwright test results to provide structured QA insights, including test metrics, failure analysis, bug report drafts, and release-quality recommendations.
README
AI QA Agent MCP
A TypeScript-based Model Context Protocol server that analyzes Playwright test results and provides structured QA insights.
Project Goal
This project demonstrates how an AI agent can use MCP tools to:
- Discover Playwright test-result files
- Calculate test execution metrics
- Analyze failed and flaky tests
- Group similar failures
- Generate QA execution summaries
- Create draft bug reports
- Provide release-quality recommendations
Planned MCP Capabilities
Tools
list_test_runsget_test_run_summaryanalyze_test_failuresgenerate_bug_reportgenerate_qa_summary
Resource
test-run://latest
Prompt
prepare-release-quality-report
Technology Stack
- Node.js
- TypeScript
- Model Context Protocol TypeScript SDK
- Zod
- Vitest
- Playwright JSON and JUnit reports
- GitHub Actions
- MCP Inspector
- Codex CLI
Planned Architecture
Playwright Test Results
|
v
Report Parsers
|
v
QA Analysis Services
|
v
MCP Server
| | |
Tools Resources Prompts
|
v
MCP Inspector or AI Client
Project Structure
ai-qa-agent-mcp/
├── .github/
│ └── workflows/
├── docs/
├── reports/
├── sample-data/
│ ├── json/
│ └── junit/
├── src/
│ ├── config/
│ ├── parsers/
│ ├── prompts/
│ ├── resources/
│ ├── schemas/
│ ├── services/
│ ├── tools/
│ ├── types/
│ └── server.ts
├── tests/
│ ├── integration/
│ └── unit/
├── .gitignore
├── package.json
├── README.md
└── tsconfig.json
Development Commands
Install dependencies:
npm install
Run the server during development:
npm run dev
Check TypeScript:
npm run typecheck
Run automated tests:
npm test
Build the project:
npm run build
Run all validations:
npm run check
Security Principles
- Read-only report access by default
- Restricted file-system access
- Input validation for every MCP tool
- No automatic issue creation
- No secret values in logs
- Human review required for AI-generated conclusions
Current Status
Version 0.1.0 is under development.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.