atlassian-mcp

atlassian-mcp

Enables AI agents to manage Jira and Confluence directly, including issue tracking, sprint management, and knowledge base operations through natural language.

Category
访问服务器

README

🚀 Atlassian FastMCP Server 🛠️

Welcome to the Atlassian FastMCP Server! 🌟 This project is a blazingly fast, lightweight Model Context Protocol (MCP) server that seamlessly integrates Atlassian tools like Jira and Confluence directly into your AI workflows! 🤖✨


🎯 What does this do?

This MCP server provides a set of highly useful tools that allow AI agents to manage your Atlassian ecosystem effortlessly. From fetching current profiles to creating sprints and generating tickets, this server brings agile management straight to your fingertips! 🖐️💻

🛠️ Available Tools

📝 Jira Management

  • get_current_user 👤: Fetch the profile of the currently authenticated Jira/Atlassian user.
  • get_projects 🗂️: Get a beautiful list of all Jira projects in your workspace.
  • search_issues 🔍: Run powerful JQL (Jira Query Language) queries to find exactly the tickets you need!
  • create_issue ➕: Quickly spin up new tasks, stories, or bugs directly in a specified project!

🏃‍♂️ Agile & Sprint Operations (NEW! 🎉)

  • get_boards 📋: Fetch agile boards (with optional filtering by project key) to find where your sprints live!
  • create_sprint 🏃: Generate a brand new Sprint for your team's board, complete with custom goals! 🥅
  • update_sprint 🔄: Manage your sprint's lifecycle! Start an active sprint with start/end dates, or close out a finished one! 🏁

📚 Confluence Knowledge Base

  • get_confluence_spaces 🌌: Discover all the knowledge spaces available in your Confluence instance.
  • search_confluence 🕵️‍♂️: Use CQL (Confluence Query Language) to find documents, meeting notes, and specs.
  • get_confluence_page 📄: Pull the rich content (body storage) of any specific Confluence page by its ID!
  • create_confluence_page ✍️: Create brand new Confluence pages directly from your AI (supports parent pages)!

🔐 Setup & Authentication 🗝️

To get this bad boy running, you need to provide your Jira credentials. The server loads your credentials directly from a .env file (which is safely ignored by Git! 🤫).

  1. Create a .env file in the root of the project.
  2. Add your credentials:
    JIRA_EMAIL=your.email@example.com
    JIRA_API_TOKEN=your_atlassian_api_token
    ATLASSIAN_URL=https://your-domain.atlassian.net
    ATLASSIAN_READ_ONLY=false
    

🔑 How to get your Atlassian API Key:

  1. Go to your Atlassian Account Security page.
  2. Click Create API token.
  3. Give it a memorable label (e.g., "FastMCP Server").
  4. Copy the token and paste it into your .env file!

🚀 Running the Server

Make sure you have your dependencies installed:

pip install -r requirements.txt

Then, fire up the server! 🔥

python server.py

The server will start up and listen on standard input/output (stdio) for fast, secure MCP communication! 🚄


⚙️ MCP Client Configuration 🔌

To use this server with your favorite MCP client (like Claude Desktop, Cursor, or Antigravity), simply add it to your client's configuration file (e.g., mcp_config.json or claude_desktop_config.json):

{
  "mcpServers": {
    "atlassian-mcp": {
      "command": "python",
      "args": [
        "/absolute/path/to/atlassian-mcp/server.py"
      ]
    }
  }
}

Note: Make sure to replace /absolute/path/to/ with the actual path where you cloned this repository! 🗺️


🤝 Contributing & Updates

Want to add more Jira magic? 🧙‍♂️ Feel free to fork, update server.py, and run the included update_config.py scripts to sync your fresh tools!

Happy building! 👷‍♀️🎉

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