QA Prompts MCP Server
Provides prompt templates and tools for mobile QA automation, including converting manual tests to Appium scripts, analyzing failures, and standardizing bug reports.
README
QA Prompts MCP Server
An MCP (Model Context Protocol) server that provides QA prompt templates for mobile automation teams. It exposes structured prompts and tools for automation code generation, failure analysis, and bug standardization — all usable directly inside Cursor.
Quick Start (No Clone Required)
Add this to your Cursor MCP config file (~/.cursor/mcp.json):
{
"mcpServers": {
"qa-prompts": {
"command": "npx",
"args": ["-y", "github:swapnilGirishPawar/Custom-MCP-Server-Mobile-QA"]
}
}
}
Restart Cursor. The prompts will be available immediately via the / slash command in chat.
This server also exposes the same capabilities as MCP tools, which can be invoked by MCP clients (and may be used automatically by Cursor when tool-calling is enabled).
Available Prompts (Slash Commands)
1. Manual → Automation Conversion
| Prompt | What It Does |
|---|---|
/convert-manual-to-automation |
Converts manual test cases into Appium + Java + TestNG automation scripts following POM architecture |
/refactor-automation-code |
Performs a deep PR review of existing automation code and generates a structured review report |
/xml-to-pom-locators |
Converts Appium Inspector Page Source XML into POM locator declarations (ID > Accessibility > XPath priority) |
2. Debugging & Failure Analysis
| Prompt | What It Does |
|---|---|
/analyze-test-failure |
Analyzes Appium test failure logs to determine root cause, severity, flakiness risk, and fix recommendations |
3. Bug Standardization
| Prompt | What It Does |
|---|---|
/standardize-bug-report |
Converts a bug title/description into a standardized bug report following the organization template |
Available Tools (MCP Tools)
Each prompt is also registered as an MCP tool with the same name (without the leading /).
| Tool | What It Does |
|---|---|
convert-manual-to-automation |
Converts manual test cases into Appium + Java + TestNG automation scripts following POM architecture |
refactor-automation-code |
Performs a deep PR review of existing automation code and generates a structured review report |
xml-to-pom-locators |
Converts Appium Inspector Page Source XML into POM locator declarations (ID > Accessibility > XPath priority) |
analyze-test-failure |
Analyzes Appium test failure logs to determine root cause, severity, flakiness risk, and fix recommendations |
standardize-bug-report |
Converts a bug title/description into a standardized bug report following the organization template |
Notes:
standardize-bug-reporttool output: the tool output format does not include a<Title>line; it returns only [Issue], [Reproduction steps], [Screenshot], [Expected Result] (with those headings expected to be bold).
Usage
- Open Cursor chat (
Cmd+L) or Composer (Cmd+I) - Type
/to see the list of available prompts - Select a prompt
- Fill in the required inputs
- Submit — the AI processes the full prompt template and returns structured output
Example: Standardize a Bug Report
- Type
/standardize-bug-reportin chat - Fill in:
- bugDescription:
login button not working on iOS after update - additionalContext (optional):
Build 2.3.1, iPhone 15, Premium account
- bugDescription:
- The AI generates a complete standardized bug report (including a rewritten title), issue, reproduction steps, and expected result
Example: Convert Manual Test Case to Automation
- Type
/convert-manual-to-automationin chat - Fill in:
- featureNavigation:
Settings → Notifications → Push Notifications - manualTestCase: (paste your manual test case)
- existingCode (optional): (paste any existing Page Objects or BaseTest for context)
- featureNavigation:
- The AI generates a complete TestNG test class with POM, annotations, and framework conventions
Prompt / Tool Inputs Reference
| Name | Required Inputs | Optional Inputs |
|---|---|---|
convert-manual-to-automation |
featureNavigation, manualTestCase |
existingCode |
refactor-automation-code |
code |
— |
xml-to-pom-locators |
pageSourceXml |
— |
analyze-test-failure |
failureLogs |
— |
standardize-bug-report |
bugDescription |
additionalContext |
Local Development
# Clone the repo
git clone https://github.com/swapnilGirishPawar/Custom-MCP-Server-Mobile-QA.git
cd Custom-MCP-Server-Mobile-QA
# Install dependencies
npm install
# Build
npm run build
# Run locally
npm start
For development with auto-reload, use npm run dev (requires tsx).
To test locally before pushing, point your MCP config to the local build:
{
"mcpServers": {
"qa-prompts": {
"command": "node",
"args": ["/absolute/path/to/Custom-MCP-Server-Mobile-QA/dist/index.js"]
}
}
}
Tech Stack
- TypeScript with strict mode
- @modelcontextprotocol/sdk v1.27+
- Zod v4 for input validation
- stdio transport for Cursor integration
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。