Jira MCP Server
Enables AI assistants to interact with Jira Cloud issues, supporting create, read, update, delete, search, and transition operations via natural language.
README
Jira MCP Server
A Model Context Protocol (MCP) server for Jira Cloud that enables AI assistants to interact with Jira issues.
Features
| Tool | Description |
|---|---|
| create_issue | Create a new Jira issue (Story, Bug, Task, Epic, etc.) |
| get_issue | Get detailed information about a specific Jira issue |
| list_issues | Search for issues using JQL (Jira Query Language) |
| get_issue_fields | Get all fields (including custom fields) for an issue |
| update_issue | Update an existing issue (summary, description, assignee, priority, labels, custom fields) |
| delete_issue | Delete a Jira issue by key or ID (with optional subtask deletion) |
| add_comment | Add a comment to a Jira issue |
| get_transitions | Get available status transitions for an issue |
| transition_issue | Transition an issue to a new status |
Prerequisites
- Node.js 18+ or Bun runtime
- Jira Cloud account with API access
- API token from Atlassian API Tokens
Installation
The easiest way to use this MCP server is via npx or bunx - no installation required! Just configure your MCP client as shown below.
If you prefer to install globally:
# Using npm
npm install -g @carmeloricarte/jira-mcp-server
# Using Bun
bun install -g @carmeloricarte/jira-mcp-server
Environment Variables
Important: You do NOT need to set environment variables at the system or user level. The MCP client will pass them to the server process when it starts. Just configure them in the
envobject of your MCP configuration.
| Variable | Description | Example |
|---|---|---|
JIRA_HOST |
Your Jira Cloud domain (without https://) | your-company.atlassian.net |
JIRA_EMAIL |
Email associated with your Atlassian account | user@example.com |
JIRA_API_TOKEN |
API token generated from Atlassian | ATATT3xF... |
MCP Client Configuration
Note: All examples below use
npx(Node.js). If you prefer Bun, replace"command": "npx"with"command": "bunx"and remove the"-y"from args.
⚠️ Windows Configuration
On Windows, you must wrap npx or bunx commands with cmd /c. Use this format:
{
"command": "cmd",
"args": ["/c", "npx", "-y", "@carmeloricarte/jira-mcp-server"]
}
Or with Bun:
{
"command": "cmd",
"args": ["/c", "bunx", "@carmeloricarte/jira-mcp-server"]
}
Important: The package name must always be the last argument in the args array.
Claude Code
Config file location:
- macOS/Linux:
~/.claude/settings.json - Windows:
%USERPROFILE%\.claude\settings.json
{
"mcpServers": {
"jira": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
VS Code (Copilot MCP Extension)
Config file location:
- macOS/Linux:
~/.vscode/mcp.jsonor workspace.vscode/mcp.json - Windows:
%USERPROFILE%\.vscode\mcp.jsonor workspace.vscode\mcp.json
{
"servers": {
"jira": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Cursor
Config file location:
- macOS:
~/Library/Application Support/Cursor/User/globalStorage/cursor.mcp/mcp.json - Windows:
%APPDATA%\Cursor\User\globalStorage\cursor.mcp\mcp.json
{
"mcpServers": {
"jira": {
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Zed
Config file location:
- macOS:
~/.config/zed/settings.json - Windows:
%APPDATA%\Zed\settings.json
{
"language_models": {
"mcp_servers": {
"jira": {
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
}
OpenCode
Config file location:
- macOS/Linux:
~/.config/opencode/config.json - Windows:
%USERPROFILE%\.config\opencode\config.json
{
"mcp_servers": {
"jira": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Codex (OpenAI CLI)
Config file location:
- macOS/Linux:
~/.codex/config.json - Windows:
%USERPROFILE%\.codex\config.json
{
"mcpServers": {
"jira": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Windsurf (Codeium)
Config file location:
- macOS:
~/.codeium/windsurf/mcp_config.json - Windows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"jira": {
"command": "npx",
"args": ["-y", "@carmeloricarte/jira-mcp-server"],
"env": {
"JIRA_HOST": "your-company.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}
Tool Examples
Create Issue
Create a new Story in project PROJ with title "Implement user authentication"
Create an Epic in PROJ called "[EPIC] Payment System" with description "Complete payment integration"
Get Issue
Get issue PROJ-123
Search Issues with JQL
Search for issues: project = PROJ AND status = "In Progress"
Update Issue
Update PROJ-123: change priority to High and add labels "urgent", "frontend"
Update the description of PROJ-123 to "Updated requirements..."
Delete Issue
Delete issue PROJ-123
Delete PROJ-456 and all its subtasks
Add Comment
Add comment "Working on this now" to PROJ-123
Transition Issue
Move PROJ-123 to "In Progress"
Development
Clone and install dependencies
git clone https://github.com/carmeloricarte/jira-mcp-server.git
cd jira-mcp-server
bun install
Run tests
bun test
Run tests with coverage
bun test --coverage
Run the server standalone
JIRA_HOST=your-company.atlassian.net \
JIRA_EMAIL=your-email@example.com \
JIRA_API_TOKEN=your-token \
bun run start
Troubleshooting
Server not starting
- Verify Node.js 18+ or Bun is installed:
node --versionorbun --version - Try running manually:
npx -y @carmeloricarte/jira-mcp-serverorbunx @carmeloricarte/jira-mcp-server - Check for any error messages in your MCP client logs
Authentication errors
- Verify your API token is valid at Atlassian API Tokens
- Ensure
JIRA_HOSTdoes not includehttps:// - Verify
JIRA_EMAILmatches the email used to generate the token
Empty results from list_issues
The server includes default fields (summary, status, priority, issuetype, assignee, updated). If you need additional fields, pass them in the fields parameter.
Contributing
Contributions are welcome! If you'd like to contribute to this project:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'feat: add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Guidelines
- Follow the existing code style
- Write tests for new features
- Update documentation as needed
- Use Conventional Commits for commit messages
Reporting Issues
Found a bug or have a feature request? Please open an issue with as much detail as possible.
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。