jira-mcp
Provides integration with Atlassian products, enabling management of Jira and Confluence resources.
Offers tools for searching, creating, updating, and managing Confluence pages and content.
Provides tools for searching, creating, updating, transitioning, and managing Jira issues, including attachments and comments.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jira-mcpFind my open tasks in the PROJ project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Atlassian
Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Supports both Cloud and Server/Data Center deployments.
https://github.com/user-attachments/assets/35303504-14c6-4ae4-913b-7c25ea511c3e
https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785
本機修改版連線指南(zh-TW)
這是基於 sooperset/mcp-atlassian 的本機修改版, 額外新增 4 個 Jira 圖片/附件工具(上游沒有):
工具
用途
jira_upload_attachment上傳附件(本機路徑或 base64)
jira_embed_image_in_description上傳圖片並嵌入描述內文渲染,支援
append/prepend/marker三種定位(marker 模式可把圖放進表格儲存格)
jira_add_comment_with_image新增留言並內嵌圖片
jira_delete_attachment刪除附件(用 attachment id 或 issue+檔名)
A. 第一次連 MCP(從零開始)
1. 取得 Jira API Token
到 https://id.atlassian.com/manage-profile/security/api-tokens 按「Create API token」, 複製產生的 token(只會顯示一次)。
2. 安裝 uv 與專案依賴
# 安裝 uv(已安裝可跳過)
curl -LsSf https://astral.sh/uv/install.sh | sh
# 取得本專案並安裝依賴
git clone <本 repo 位址> ~/jira-mcp # 或放任何路徑
cd ~/jira-mcp
uv sync3. 設定 Claude Desktop
編輯設定檔(沒有就新建):
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"mcp-atlassian": {
"command": "uv",
"args": [
"--directory",
"/你的絕對路徑/jira-mcp",
"run",
"mcp-atlassian"
],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "你的 API token"
}
}
}
}注意事項:
--directory後面要填本 repo 的絕對路徑(不能用~)若
uv不在系統 PATH,command請填完整路徑(用which uv查,通常是~/.local/bin/uv,要展開成絕對路徑)token 一律放在設定檔的
env區,不要寫進任何會 commit 的檔案也要用 Confluence 的話,在
env加上CONFLUENCE_URL(https://your-company.atlassian.net/wiki)、CONFLUENCE_USERNAME、CONFLUENCE_API_TOKEN
4. 重啟並驗證
完全結束 Claude Desktop(macOS 按 Cmd+Q,不是只關視窗)再重開。 對 Claude 說「列出我在 Jira 的專案」,有正常回應即連線成功; 說「把某張本機圖片嵌入某張票的描述」可驗證本修改版專屬工具。
B. 從官方發佈版(uvx / Docker)切換到本修改版
如果你原本已經照官方 README 用 uvx mcp-atlassian 或 Docker 跑,
只需要改 command / args 兩個欄位,env 整段保留不動:
{
"mcpServers": {
"mcp-atlassian": {
- "command": "uvx",
- "args": ["mcp-atlassian"],
+ "command": "uv",
+ "args": [
+ "--directory",
+ "/你的絕對路徑/jira-mcp",
+ "run",
+ "mcp-atlassian"
+ ],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token"
}
}
}
}Docker 版同理:把整個 command/args 換成上面 uv --directory ... run mcp-atlassian 的形式即可。
差異說明:
uvx mcp-atlassian跑的是 PyPI 上的官方發佈版,沒有本修改版的 4 個圖片/附件工具uv --directory <路徑> run mcp-atlassian跑的是這個資料夾裡的原始碼,改完程式碼後重啟 Claude Desktop 就生效,不需要重新安裝想換回官方版,把
command/args改回原樣即可,隨時可逆
改完設定後一樣要完全重啟 Claude Desktop 才會生效。
Related MCP server: MCP Atlassian
Quick Start
1. Get Your API Token
Go to https://id.atlassian.com/manage-profile/security/api-tokens and create a token.
For Server/Data Center, use a Personal Access Token instead. See Authentication.
2. Configure Your IDE
Add to your Claude Desktop or Cursor MCP configuration:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token",
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token"
}
}
}
}Server/Data Center users: Use
JIRA_PERSONAL_TOKENinstead ofJIRA_USERNAME+JIRA_API_TOKEN. See Authentication for details.
3. Start Using
Ask your AI assistant to:
"Find issues assigned to me in PROJ project"
"Search Confluence for onboarding docs"
"Create a bug ticket for the login issue"
"Update the status of PROJ-123 to Done"
Documentation
Full documentation is available at mcp-atlassian.soomiles.com.
Documentation is also available in llms.txt format, which LLMs can consume easily:
llms.txt— documentation sitemapllms-full.txt— complete documentation
Topic | Description |
uvx, Docker, pip, from source | |
API tokens, PAT, OAuth 2.0 | |
IDE setup, environment variables | |
SSE, streamable-http, multi-user | |
All Jira & Confluence tools | |
Common issues & debugging |
Compatibility
Product | Deployment | Support |
Confluence | Cloud | Fully supported |
Confluence | Server/Data Center | Supported (v6.0+) |
Jira | Cloud | Fully supported |
Jira | Server/Data Center | Supported (v8.14+) |
Key Tools
Jira | Confluence |
|
|
|
|
|
|
|
|
|
|
72 tools total — See Tools Reference for the complete list.
Security
Never share API tokens. Keep .env files secure. See SECURITY.md.
Contributing
See CONTRIBUTING.md for development setup.
License
MIT - See LICENSE. Not an official Atlassian product.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PhoebusForWork/jira-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server