atlassian-mcp
Enables Claude and Claude Code to interact with Atlassian Cloud (Confluence and Jira) through natural language, supporting full CRUD operations, search, comments, and attachments.
README
Atlassian MCP Server
An MCP (Model Context Protocol) server that enables Claude and Claude Code to interact with Atlassian Cloud (Confluence and Jira).
Features
Confluence
- Spaces: List, get details, create new spaces
- Pages: Full CRUD (create, read, update, delete)
- Comments: Read and add comments on pages
- Attachments: List and upload attachments
- Search: Query using CQL (Confluence Query Language)
Jira
- Projects: List, get details, create new projects
- Issues: Full CRUD (create, read, update, delete)
- Comments: Read and add comments on issues
- Attachments: List and upload attachments
- Search: Query using JQL (Jira Query Language)
Installation
# Clone or navigate to the project
cd atlassian-mcp
# Create a virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install the package
pip install -e .
Configuration
-
Copy the example environment file:
cp .env.example .env -
Edit
.envwith your Atlassian credentials:ATLASSIAN_DOMAIN=yourcompany # yourcompany.atlassian.net ATLASSIAN_EMAIL=you@example.com ATLASSIAN_API_TOKEN=your_api_token -
Get your API token from: https://id.atlassian.com/manage-profile/security/api-tokens
Usage
stdio Mode (for Claude Code)
# Run directly
python -m atlassian_mcp --stdio
# Or using the installed command
atlassian-mcp --stdio
SSE Mode (HTTP Server)
# Run the HTTP server
python -m atlassian_mcp --sse
# Server will start on http://127.0.0.1:8000
# SSE endpoint: http://127.0.0.1:8000/sse
# Health check: http://127.0.0.1:8000/health
Claude Code Configuration
Add to your Claude Code settings (~/.claude/settings.json or project-level):
{
"mcpServers": {
"atlassian": {
"command": "/path/to/atlassian-mcp/.venv/bin/python",
"args": ["-m", "atlassian_mcp", "--stdio"],
"cwd": "/path/to/atlassian-mcp"
}
}
}
The server reads credentials from the .env file in the project directory, so you don't need to specify them in settings.json.
Available Tools
Confluence Tools
| Tool | Description |
|---|---|
confluence_list_spaces |
List all Confluence spaces |
confluence_get_space |
Get space details by key |
confluence_create_space |
Create a new space |
confluence_list_pages |
List pages (optionally by space) |
confluence_get_page |
Get page content by ID |
confluence_create_page |
Create a new page |
confluence_update_page |
Update an existing page |
confluence_delete_page |
Delete a page |
confluence_search |
Search using CQL |
confluence_get_comments |
Get comments on a page |
confluence_add_comment |
Add a comment to a page |
confluence_list_attachments |
List page attachments |
confluence_upload_attachment |
Upload attachment to page |
Jira Tools
| Tool | Description |
|---|---|
jira_list_projects |
List all Jira projects |
jira_get_project |
Get project details by key |
jira_create_project |
Create a new project |
jira_search_issues |
Search using JQL |
jira_get_issue |
Get issue details by key |
jira_create_issue |
Create a new issue |
jira_update_issue |
Update an existing issue |
jira_delete_issue |
Delete an issue |
jira_get_comments |
Get comments on an issue |
jira_add_comment |
Add a comment to an issue |
jira_list_attachments |
List issue attachments |
jira_upload_attachment |
Upload attachment to issue |
Example Queries
Confluence CQL Examples
type=page AND space=TEAM
text ~ "search term"
creator=currentUser() AND created > now("-7d")
label=important
Jira JQL Examples
project = PROJ
assignee = currentUser() AND status != Done
created >= -7d ORDER BY created DESC
labels = bug AND priority = High
Development
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Format code
ruff format .
# Lint
ruff check .
License
MIT
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。