Jira MCP Integration
Enables AI agents to interact with Jira Cloud through the REST API, supporting project management, issue operations (create, read, update, delete), JQL search, task assignments, and status transitions.
README
🔌 Jira MCP Integration
Cursor AI and other agents write amazing code. In enterprises, tasks are given in instruments like Jira, GitHub Issues, Azure DevOps. AI needs access to such instruments.
This open-source solution helps AI agents work with Jira data.
🌐 Public Instance
Available at https://jira-mcp.koveh.com
Just provide your Jira credentials. We don't store any data.
Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ AI Agent │────▶│ MCP Server │────▶│ Jira Cloud │
│ (Cursor/etc) │◀────│ jira-mcp │◀────│ REST API │
└─────────────────┘ └─────────────────┘ └─────────────────┘
Features
- ✅ Get list of projects
- ✅ Get list of tasks with details
- ✅ Get specific task with descriptions
- ✅ Create new tickets
- ✅ Update existing tickets
- ✅ Delete tickets
- ✅ Search using JQL
- ✅ Assign tasks to users
- ✅ Transition task status
Quick Start
Option 1: Use Public Instance
Go to https://jira-mcp.koveh.com and connect with your Jira credentials.
Option 2: Run with Docker
git clone https://github.com/Koveh/jira-mcp.git
cd jira-mcp
docker-compose up -d
Access at http://localhost:4200
Option 3: Run Locally
git clone https://github.com/Koveh/jira-mcp.git
cd jira-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
python http_server.py
Get Jira API Token
- Go to https://id.atlassian.com/manage-profile/security/api-tokens
- Click "Create API token"
- Copy the token
Usage
Add to Cursor IDE (Local MCP)
- Clone and set up virtual environment:
git clone https://github.com/Koveh/jira-mcp.git
cd jira-mcp
# Create virtual environment (required for mcp package)
python3 -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
-
Get your Jira API token from: https://id.atlassian.com/manage-profile/security/api-tokens
-
Add to
~/.cursor/mcp.json(macOS/Linux) or%USERPROFILE%\.cursor\mcp.json(Windows):
{
"mcpServers": {
"jira": {
"command": "/full/path/to/jira-mcp/venv/bin/python",
"args": ["/full/path/to/jira-mcp/mcp_server.py"],
"env": {
"JIRA_BASE_URL": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token-from-step-2"
}
}
}
}
Important: Use the full path to the Python interpreter inside the venv (
venv/bin/pythonon Linux/macOS,venv\Scripts\python.exeon Windows). This ensures themcppackage is available.
- Restart Cursor (Cmd/Ctrl+Shift+P → "Developer: Reload Window")
You'll have these tools available:
| Tool | Description |
|---|---|
jira_connect |
Connect to Jira instance |
jira_get_projects |
List all projects |
jira_get_issues |
Get issues from project |
jira_get_issue |
Get specific issue details |
jira_create_issue |
Create new issue |
jira_update_issue |
Update existing issue |
jira_delete_issue |
Delete issue |
jira_search |
Search with JQL |
jira_get_current_user |
Get current user info |
REST API Usage
# 1. Connect and get token
curl -X POST https://jira-mcp.koveh.com/api/connect \
-H "Content-Type: application/json" \
-d '{
"base_url": "https://your-domain.atlassian.net",
"email": "your-email@example.com",
"api_token": "your-api-token"
}'
# Response includes token for subsequent requests
# {"status": "connected", "token": "eyJ...", ...}
# 2. Use token for API calls
curl https://jira-mcp.koveh.com/api/projects \
-H "Authorization: Bearer YOUR_TOKEN"
# 3. Create issue
curl -X POST https://jira-mcp.koveh.com/api/issues \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"project": "PROJ", "summary": "New task"}'
CLI Usage
export JIRA_BASE_URL=https://your-domain.atlassian.net
export JIRA_EMAIL=your-email@example.com
export JIRA_API_TOKEN=your-api-token
python cli.py whoami # Show current user
python cli.py projects # List projects
python cli.py list PROJ # List issues
python cli.py get PROJ-123 # Get issue details
python cli.py create PROJ "Summary" # Create issue
python cli.py update PROJ-123 -s "New" # Update issue
python cli.py delete PROJ-123 # Delete issue
python cli.py search "status='Done'" # Search with JQL
Python Client
from jira_client import JiraClient, JiraConfig
config = JiraConfig(
base_url="https://your-domain.atlassian.net",
email="your-email@example.com",
api_token="your-api-token"
)
client = JiraClient(config)
# Get projects
projects = client.get_all_projects()
# Create issue
issue = client.create_issue("PROJ", "Summary", "Description")
# Search
results = client.search_issues("status = 'In Progress'")
API Endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET | /health |
Health check |
| POST | /api/connect |
Connect and get token |
| GET | /api/user |
Get current user |
| GET | /api/projects |
List all projects |
| GET | /api/issues?project=KEY |
Get project issues |
| GET | /api/issue/KEY |
Get issue details |
| POST | /api/issues |
Create issue |
| PUT | /api/issue/KEY |
Update issue |
| DELETE | /api/issue/KEY |
Delete issue |
| GET | /api/search?jql=... |
Search with JQL |
Project Structure
jira-mcp/
├── jira_client.py # Core Jira API wrapper
├── mcp_server.py # MCP server (stdio transport)
├── http_server.py # HTTP/REST server
├── cli.py # Command-line interface
├── Dockerfile # Docker image
├── docker-compose.yml # Docker Compose config
├── requirements.txt # Python dependencies
├── examples/ # Usage examples
│ ├── cursor_mcp_config.json
│ └── api_usage.sh
└── tests/ # Test scripts
├── test_jira.py
└── demo.py
Self-Hosting with Docker
# Build and run
docker-compose up -d
# Or manually
docker build -t jira-mcp .
docker run -d -p 4200:4200 --name jira-mcp jira-mcp
With nginx reverse proxy
server {
server_name jira-mcp.yourdomain.com;
location / {
proxy_pass http://127.0.0.1:4200;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
}
}
SSL with Certbot
certbot --nginx -d jira-mcp.yourdomain.com
Security
- 🔒 We don't store any credentials or data
- 🔑 Credentials are only used for direct Jira API calls
- 📤 Use API tokens (not passwords)
- 🔄 Tokens can be revoked anytime at id.atlassian.com
License
MIT
Author
DHW Team - koveh.com
Made with ❤️ for the AI-powered development community
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。