Jira MCP Server
Enables AI agents to interact with Jira Cloud, including listing boards and issues, adding comments, and searching users.
README
Jira MCP Server
A modular, extensible Model Context Protocol (MCP) server for interacting with Jira Cloud. This project provides a set of tools to query boards, issues, user information, and more, making it easy to integrate Jira with AI agents, bots, or other automation systems.
🚀 Features
- List all available Jira scrum boards
- List your own issues for a specific board
- Add comments to Jira issues (ADF-compliant)
- Get current authenticated user information
- Search for users by login, email, or display name
- Get Jira server information (including server time)
- Modular, extensible, and easy to contribute
🛠️ Requirements
- Node.js 18+
- Access to a Jira Cloud instance
- Jira API Token (see Jira API Tokens)
⚙️ Environment Variables
Set the following environment variables in your shell or .env file:
JIRA_BASE_URL=https://your-domain.atlassian.net
JIRA_EMAIL=your-email@company.com
JIRA_API_TOKEN=your-jira-api-token
🚀 Quick Start (with npx)
You can run the Jira MCP Server instantly with npx, no global install required:
npx -y @ahmetbarut/jira-mcp-server
Or, if you want to use it as an MCP tool in a config file (e.g. mcp.json):
{
"Jira MCP Server": {
"command": "npx",
"args": ["-y", "@ahmetbarut/jira-mcp-server"],
"env": {
"JIRA_BASE_URL": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "your-email@company.com",
"JIRA_API_TOKEN": "your-jira-api-token"
}
}
}
- No need for
npm installor global install. - All dependencies are handled by
npx. - You can set your Jira credentials in the
envsection.
Note: The first run may take a few seconds as
npxdownloads the package.
📦 Installation & Setup
- Clone the repository (optional):
git clone https://github.com/ahmetbarut/jira-mcp.git cd jira-mcp-server - Install globally (optional):
npm install -g @ahmetbarut/jira-mcp-server - Set environment variables:
- See above for required variables.
- Build the project (if using from source):
npm run build - Run the server:
jira-mcp-server # or npx -y @ahmetbarut/jira-mcp-server
🧩 Usage
This server is designed to be used as an MCP tool server, typically via stdio. You can interact with it using the Model Context Protocol Inspector or integrate it into your own MCP-compatible agent.
Example: List Boards
npx @modelcontextprotocol/inspector --cli npx -y @ahmetbarut/jira-mcp-server --method tools/call --tool-name get_boards
Example: Get Your Issues for a Board
npx @modelcontextprotocol/inspector --cli npx -y @ahmetbarut/jira-mcp-server --method tools/call --tool-name get_issues --tool-arg boardId=123
Example: Add a Comment to an Issue
npx @modelcontextprotocol/inspector --cli npx -y @ahmetbarut/jira-mcp-server --method tools/call --tool-name add_comment_to_issue --tool-arg issueIdOrKey=PROJ-123 --tool-arg body="This is a test comment."
🧰 Available Tools
- get_boards: List all available Jira scrum boards
- get_issues: List your issues for a specific board
- add_comment_to_issue: Add a comment to a Jira issue (ADF-compliant)
- get_current_user_info: Get current authenticated user information
- search_user: Search for a user by login, email, or display name
- get_server_info: Get Jira server information (including server time)
🏗️ Project Structure
src/index.ts— Main server entry point and tool dispatchersrc/tools.ts— Tool definitions and schemassrc/handlers.ts— Tool handler implementations (business logic)src/jiraApi.ts— Jira API helpers and configurationsrc/types.ts— TypeScript types and interfaces
🤝 Contributing
Contributions are welcome! Please follow these steps:
- Fork the repository
- Create a new branch for your feature or bugfix:
git checkout -b my-feature - Write clear, well-documented code
- Add or update tests if applicable
- Open a pull request with a clear description of your changes
- Ensure your code passes lint and build checks
Code Style
- Use TypeScript and follow the existing modular structure
- Keep business logic in
handlers.tsand API helpers injiraApi.ts - Write clear commit messages
Issues
If you find a bug or have a feature request, please open an issue on GitHub with as much detail as possible.
📄 License
This project is licensed under the MIT License. See LICENSE for details.
Happy automating with Jira MCP Server!
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。