QA MCP Server
An AI-powered QA automation server that integrates Jira, GitHub, Jenkins, AWS, and Webex into a unified interface for QA engineers.
README
QA MCP Server
An AI-powered QA automation server built on the Model Context Protocol (MCP). Integrates Jira, GitHub, Jenkins, AWS, and Webex into a unified interface for QA engineers.
Tool catalog: dwonng.github.io/qa-mcp-server — auto-generated from the
@mcp.tool()decorators inqa_mcp/server.pyon every push tomain.
Features
Jira Integration
- Find tickets ready for QA or in progress
- Claim tickets for validation (assign + set validator + update status)
- Mark tickets as passed/failed with formatted comments
- Generate AI-powered test cases from ticket descriptions
- Summarize comment threads
- Analyze stories and epics for QA readiness
GitHub Integration
- Find PRs linked to Jira tickets
- Check PR merge status and commit details
- Verify code changes before testing
Jenkins Integration
- Check E2E test results
- Trigger builds with custom parameters
- Monitor build history
- Wait for builds and update PR descriptions with results
AWS Integration
- Verify Lambda deployments via last-modified timestamps
- Compare deployments across environments
- Confirm code is deployed before testing
Webex Integration
- List and read messages from Webex rooms
- Search for discussions about specific topics
- Post updates and notifications
- AI-powered conversation summaries
Quick Start
Prerequisites
- Python 3.11+
- Docker (recommended) or local Python environment
- API tokens for the services you want to use
Quick Install (Pre-built Image)
Add to your MCP configuration (~/.cursor/mcp.json):
{
"mcpServers": {
"qa-automation": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "JIRA_URL=https://your-jira.atlassian.net",
"-e", "JIRA_PERSONAL_TOKEN=your_token",
"-e", "GITHUB_TOKEN=ghp_your_token",
"ghcr.io/dwonng/qa-mcp-server:latest"
]
}
}
}
Full Installation
-
Clone the repository
git clone https://github.com/DwonnG/qa-mcp-server.git cd qa-mcp-server -
Create your config
cp config_example.py config.py # Edit config.py with your Jira field IDs, Jenkins paths, etc. -
Add to your MCP client with all integrations:
{ "mcpServers": { "qa-automation": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "JIRA_URL=https://your-jira.atlassian.net", "-e", "JIRA_PERSONAL_TOKEN=your_token", "-e", "GITHUB_HOST=https://api.github.com", "-e", "GITHUB_TOKEN=ghp_your_token", "-e", "JENKINS_URL=https://your-jenkins.com", "-e", "JENKINS_USER=your_user", "-e", "JENKINS_TOKEN=your_token", "-e", "AWS_REGION=us-east-1", "-e", "WEBEX_TOKEN=your_webex_token", "-v", "$HOME/.aws:/root/.aws:ro", "-v", "$HOME/.config/qa-mcp-server/config.py:/app/config.py:ro", "ghcr.io/dwonng/qa-mcp-server:latest" ] } } }
Note: Mount your
config.pyfor custom JQL templates, field mappings, and Jenkins job paths.
Local Development
# Create virtual environment
python -m venv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
# Install dependencies
pip install -r requirements.txt
# Run the server
python run.py
Configuration
config.py
This file contains organization-specific settings:
| Setting | Description |
|---|---|
JIRA_FIELDS |
Custom field IDs for your Jira instance |
JIRA_TRANSITIONS |
Workflow transition IDs |
REPO_LAMBDA_MAP |
Maps repos to Lambda function names |
JENKINS_JOBS |
Jenkins job paths |
JQL_TEMPLATES |
JQL query templates |
RELEASE_TESTING |
Template Epic key for release testing cloning |
See config_example.py for a template with documentation.
Environment Variables
| Variable | Required | Description |
|---|---|---|
JIRA_URL |
Yes | Your Jira instance URL |
JIRA_PERSONAL_TOKEN |
Yes | Jira API token or PAT |
JIRA_VERIFY_SSL |
No | Set to false for self-signed certs |
GITHUB_HOST |
No | GitHub API URL (default: api.github.com) |
GITHUB_TOKEN |
Yes | GitHub personal access token |
JENKINS_URL |
Yes* | Jenkins server URL |
JENKINS_USER |
Yes* | Jenkins username |
JENKINS_TOKEN |
Yes* | Jenkins API token |
AWS_REGION |
No | AWS region (default: us-east-1) |
WEBEX_TOKEN |
No | Webex bot or personal token |
*Required only if using Jenkins features
Available Tools
Jira Tools
qa_get_qa_queue- Find tickets waiting in the QA queue ready to be testedqa_find_in_progress- Find tickets developers are working onqa_claim_ticket- Claim a ticket for QA validationqa_resolve_pass- Mark ticket as QA passedqa_fail_ticket- Mark ticket as QA failed with bug reportqa_add_comment- Add a comment to any ticketqa_generate_test_cases- AI-generated test casesqa_summarize_comments- Summarize ticket commentsqa_analyze_story- Analyze story for QA readinessqa_analyze_epic- Analyze epic for release readinessqa_clone_release_epic- Clone release testing template Epic and tasks for a new version
GitHub Tools
qa_get_pr_info- Get PR detailsqa_find_prs_for_ticket- Find PRs linked to a Jira ticketqa_find_pr_for_commit- Find PR that introduced a commit
Jenkins Tools
qa_check_e2e_tests- Check E2E test resultsqa_get_recent_builds- Get build historyqa_trigger_e2e_tests- Trigger a test buildqa_get_my_test_builds- View your Jenkins test buildsqa_wait_for_build_and_update_pr- Wait for build and update PR
AWS Tools
qa_check_deployment- Verify Lambda deploymentqa_check_all_deployments- Check all Lambdas for a repoqa_compare_environments- Compare deployments across envsqa_get_deployment_summary- Formatted deployment status
Webex Tools
webex_list_rooms- List accessible Webex roomswebex_get_messages- Read messages from a roomwebex_summarize_room- AI summary of conversationwebex_post_message- Post a messagewebex_search_messages- Search for messages
Workflow Tools
qa_get_ticket_context- Full context (Jira + PRs + deployment)qa_verify_vulnerability_resolved- Verify vuln fix: find PR, check merge, verify deployment, check tests, resolve ticketqa_verify_and_resolve_vulnerability- One-click vuln verification
1-minute demo
See DEMO_1_MINUTE.md for a scripted 1-minute demo: find ready tickets → get details → AI test cases (optional: claim ticket).
Example Usage
You: "Are there any tickets ready for QA?"
AI: Found 3 tickets in QA status...
You: "Claim PROJ-12345 for QA"
AI: Claimed! Assigned to you, validator set, status updated to In Progress.
You: "Check if the PR for PROJ-12345 is merged and deployed"
AI: PR #456 merged 2 hours ago. Lambda last modified 1 hour ago. Deployed!
You: "Mark PROJ-12345 as passed - verified login flow works correctly"
AI: Resolved as passed with QA comment added.
You: "Clone the release testing template for version 3.3.0"
AI: Created new Epic O365-50500 "Release 3.3.0 Testing" with 8 test tasks cloned.
Project Structure
qa-mcp-server/
├── run.py # Entry point
├── config.py # Your settings (git-ignored)
├── config_example.py # Settings template
├── requirements.txt # Dependencies
├── Dockerfile
├── README.md
├── LICENSE
│
├── qa_mcp/ # Main package
│ ├── __init__.py
│ ├── server.py # MCP server with all tools
│ ├── handlers.py # AI analysis handlers
│ ├── prompts.py # AI prompt templates
│ │
│ └── clients/ # Service integrations
│ ├── __init__.py
│ ├── jira.py
│ ├── github.py
│ ├── jenkins.py
│ ├── aws.py
│ ├── webex.py
│ └── ai.py
│
└── examples/ # Configuration examples
├── env.example # Environment variables template
└── mcp_config.json # MCP client config example
Architecture
┌─────────────────────────────────────────────────────────────┐
│ MCP Client │
│ (Cursor, Claude Desktop) │
└─────────────────────────┬───────────────────────────────────┘
│ MCP Protocol
┌─────────────────────────▼───────────────────────────────────┐
│ QA MCP Server │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ Jira │ │ GitHub │ │ Jenkins │ │ AWS │ │
│ │ Client │ │ Client │ │ Client │ │ Client │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
│ │ │ │ │ │
│ ┌────▼─────────────▼─────────────▼─────────────▼────┐ │
│ │ config.py │ │
│ │ (Organization-specific settings) │ │
│ └────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
Roadmap
v1.1 - Modular Integrations
- [ ] Feature flags to enable/disable integrations (Webex, Jenkins, AWS)
- [ ] Only register MCP tools for configured services
- [ ] Graceful handling when optional services aren't configured
v1.2 - Flexible Jira Support
- [ ] Make custom fields (validator, test_result) optional
- [ ] Support Jira Cloud and Jira Server/Data Center
- [ ] Configurable workflow transitions (not hardcoded IDs)
v1.3 - CI/CD Abstraction
- [ ] Abstract CI/CD interface (not just Jenkins)
- [ ] GitHub Actions support
- [ ] GitLab CI support
v1.4 - Deployment Verification
- [ ] Abstract deployment checker (not just AWS Lambda)
- [ ] Kubernetes deployment status
- [ ] Generic health check endpoints
v1.5 - Testing & Quality
- [ ] Unit tests for clients
- [ ] Integration test examples
- [ ] CI pipeline for the project itself
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details.
Acknowledgments
- Built with FastMCP
- Inspired by the need to automate repetitive QA tasks
- Thanks to the MCP community for the protocol specification
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。