Jira Context MCP Server

Jira Context MCP Server

Integrates Jira with Cursor IDE for AI-powered issue management, sprint tracking, library vulnerability analysis, and MySQL database queries through natural language.

Category
访问服务器

README

Jira Context MCP Server

A powerful Model Context Protocol (MCP) server that integrates Jira with Cursor IDE, enabling AI-powered issue management, sprint tracking, and library vulnerability analysis.

🚀 Features

  • Jira Integration: Fetch issue details, manage sprints, track progress
  • Sprint Management: View active sprints, generate reports, analyze backlog
  • Library Vulnerability Analysis: Check Maven/NPM packages for vulnerabilities and upgrade recommendations
  • Database Integration: Query MySQL databases directly from Cursor
  • Smart URL Parser: Paste any Jira board/sprint URL and get instant insights

📋 Prerequisites

  • Node.js 20.17.0 or higher
  • A Jira account with API access
  • Jira API token (Generate here)

⚙️ Installation

  1. Clone the repository:

    git clone https://github.com/Darshancisco/Appd_jira_context_mcp.git
    cd Appd_jira_context_mcp
    
  2. Install dependencies:

    npm install
    
  3. Create .env file:

    cp .env.example .env
    
  4. Configure your .env file:

    JIRA_BASE_URL=https://your-domain.atlassian.net
    JIRA_USERNAME=your-email@example.com
    JIRA_API_TOKEN=your-api-token-here
    HTTP_PORT=3000
    
  5. Build the project:

    npm run build
    

🏃 Running the Server

Start the MCP server:

npm start

The server will start on http://localhost:3000/sse

🔌 Connect to Cursor IDE

Method 1: Direct Configuration in mcp.json (Recommended)

  1. Locate your Cursor MCP configuration file:

    • macOS: ~/.cursor/mcp.json
    • Windows: %APPDATA%\.cursor\mcp.json
    • Linux: ~/.cursor/mcp.json
  2. Add the MCP server configuration:

    Edit the mcp.json file and add the following configuration:

    {
      "mcpServers": {  
        "jira-resolution": {
          "command": "node",
          "args": ["/absolute/path/to/Appd_jira_context_mcp/dist/index.js"],
          "cwd": "/absolute/path/to/Appd_jira_context_mcp",
          "env": {
            "JIRA_BASE_URL": "https://your-domain.atlassian.net",
            "JIRA_USERNAME": "your-email@example.com",
            "JIRA_API_TOKEN": "your-api-token-here",
            "DB_TYPE": "mysql",
            "DB_HOST": "localhost",
            "DB_PORT": "3306",
            "DB_USER": "root",
            "DB_PASSWORD": "your-database-password",
            "DB_NAME": "",
            "DB_SSL": "false"
          }
        }
      }
    }
    
  3. Replace the placeholders:

    • "/absolute/path/to/Appd_jira_context_mcp" → Full path to where you cloned the repo
    • "your-domain.atlassian.net" → Your Jira instance URL
    • "your-email@example.com" → Your Jira username/email
    • "your-api-token-here" → Your Jira API token
    • "your-database-password" → Your MySQL password (if using database features)
  4. Save the file and restart Cursor IDE

  5. Verify connection:

    • Open Cursor IDE
    • The MCP server should automatically connect
    • You can verify by typing commands in the chat

Method 2: Using Cursor Settings UI

  1. Open Cursor IDE
  2. Go to SettingsFeaturesModel Context Protocol
  3. Add a new MCP server with:
    • Name: Jira Context MCP
    • URL: http://localhost:3000/sse (requires server to be running separately)
  4. Click Connect

Method 3: Using Command Palette

  1. Open Command Palette (Cmd+Shift+P / Ctrl+Shift+P)
  2. Type "Connect to MCP Server"
  3. Enter: http://localhost:3000/sse (requires server to be running separately)

Note: Method 1 (mcp.json) is recommended as it starts the server automatically and doesn't require running npm start separately.

🛠️ Available Tools

Once connected, you can use these tools in Cursor:

Jira Issue Management

  • get_issue - Get detailed information about a Jira issue
  • get_assigned_issues - Get issues assigned to you
  • get_issues_by_type - Filter issues by type (Bug, Story, Epic, etc.)
  • get_projects - List all available Jira projects
  • get_issue_types - List all issue types

Sprint & Board Management

  • analyze_jira_url - Parse any Jira URL (board/sprint/issue)
  • get_boards - List all agile boards
  • get_sprints - Get sprints for a board
  • get_sprint_issues - Get all issues in a sprint
  • get_backlog - Get backlog issues
  • get_sprint_report - Generate comprehensive sprint report

Library Vulnerability Tools

  • check_maven_library - Check Maven library for vulnerabilities
  • check_npm_library - Check NPM package for vulnerabilities
  • analyze_dependencies - Analyze project dependencies
  • recommend_upgrade - Get smart upgrade recommendations
  • get_github_release_notes - Fetch release notes for library upgrades
  • find_library_usage - Find where a library is used in codebase

Database Tools

  • list_databases - List all MySQL databases
  • list_db_tables - List tables in a database
  • get_table_schema - Get table structure
  • query_database - Execute SQL queries
  • search_table - Search across table columns

💡 Example Usage

Analyze Your Sprint Board

Analyze my sprint board: https://jira.corp.appdynamics.com/secure/RapidBoard.jspa?rapidView=2823

Check Library Vulnerability

Check if org.springframework:spring-core version 5.3.0 has any vulnerabilities

Get Assigned Issues

Show me all issues assigned to me in project ABC

Sprint Report

Generate sprint report for board 2823

📁 Project Structure

.
├── src/
│   ├── index.ts              # Application entry point
│   ├── server.ts             # MCP server implementation
│   ├── cli.ts                # CLI interface
│   ├── services/             # Core services
│   │   ├── jira.ts           # Jira API integration
│   │   ├── libraryManager.ts # Library vulnerability analysis
│   │   ├── DatabaseService.ts # MySQL integration
│   │   └── ...
│   ├── types/                # TypeScript type definitions
│   └── utils/                # Utility functions
├── dist/                     # Compiled JavaScript (generated)
├── package.json              # Dependencies
├── tsconfig.json             # TypeScript config
└── .env                      # Environment variables (create this)

🔧 Development

Run in development mode:

npm run dev

Build:

npm run build

Type checking:

npm run type-check

🐛 Troubleshooting

Server won't start

  • Ensure Node.js version is 20.17.0 or higher: node --version
  • Check if port 3000 is available
  • Verify .env file is configured correctly (if using Method 2/3)
  • Run npm run build to ensure the dist/ folder exists

Can't connect in Cursor

  • If using mcp.json: Make sure the paths are absolute and correct
  • If using HTTP mode: Make sure the server is running (npm start)
  • Verify the URL is http://localhost:3000/sse
  • Check Cursor's MCP connection settings
  • Restart Cursor IDE after modifying mcp.json

Jira API errors

  • Verify your API token is valid
  • Ensure JIRA_BASE_URL matches your Jira instance
  • Check your Jira account has necessary permissions
  • Make sure there are no extra spaces in your credentials

MCP server not showing tools

  • Run npm run build to compile TypeScript
  • Check console for error messages
  • Verify all environment variables are set correctly

🔒 Security Note

Important: The mcp.json file contains sensitive credentials (API tokens, database passwords).

  • Keep your mcp.json file secure and never commit it to version control
  • The mcp.json file is stored locally on your machine
  • Only you have access to these credentials
  • Generate API tokens with minimum required permissions

📄 License

MIT License

👤 Author

Darshan Hanumanthappa

🙏 Acknowledgments

Built for AppDynamics engineering team to streamline Jira workflow integration with Cursor IDE.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选