
JIRA MCP Server
Provides tools for AI assistants to interact with JIRA APIs, enabling them to read, create, update, and manage JIRA issues through standardized MCP tools.
README
JIRA MCP Server
A Model Context Protocol (MCP) server that provides tools for interacting with JIRA APIs. This server enables AI assistants to read, create, update, and manage JIRA issues through standardized MCP tools.
Features
This MCP server provides the following tools:
- jira_get_issue: Get details of a specific JIRA issue by key
- jira_search: Search issues using JQL (JIRA Query Language) with pagination support
- jira_create_issue: Create a new issue with project, issue type, summary, and optional fields
- jira_update_issue: Update an existing issue's fields (summary, description, assignee, priority)
- jira_transition_issue: Transition an issue to a new status with optional comment
- jira_add_comment: Add a comment to an existing issue
Requirements
- Node.js 18.0 or higher
- JIRA instance with API token access
- Personal Access Token from your JIRA instance
Installation
Option 1: Quick Start with npx (Recommended)
Run the JIRA MCP server directly without installation:
npx @hackdonalds/jira-mcp
Option 2: Install Globally
Install the package globally for repeated use:
npm install -g @hackdonalds/jira-mcp
jira-mcp
Option 3: Install from Source
-
Clone this repository:
git clone <repository-url> cd jira-mcp
-
Install dependencies:
npm install
-
Run the server:
npm start
Configuration
Set up your environment variables before running:
export JIRA_BASE_URL="https://your-jira-instance.com"
export JIRA_API_TOKEN="your-api-token"
export JIRA_EMAIL="your-email@company.com" # Optional
Or create a .env
file:
cp .env.example .env
# Edit .env with your JIRA credentials
Configuration
Environment Variables
The MCP server requires the following environment variables:
- JIRA_BASE_URL: Your JIRA instance URL (without trailing slash)
- Example:
https://yourcompany.atlassian.net
orhttps://jira.yourcompany.com
- Example:
- JIRA_API_TOKEN: Your JIRA Personal Access Token
- For Atlassian Cloud: Create at id.atlassian.com/manage-profile/security/api-tokens
- For Server/Data Center: Create in your JIRA profile settings
Authentication
This server uses Bearer token authentication with Personal Access Tokens. The JIRA_EMAIL environment variable is optional and only used for logging purposes.
Supported JIRA versions:
- Atlassian Cloud
- JIRA Server 9.0+
- JIRA Data Center
Usage
Starting the Server
Using npx (if not installed globally):
npx @hackdonalds/jira-mcp
If installed globally:
jira-mcp
From source:
npm start
Or run directly:
node server.js
Example Tool Usage
Search Issues
// Search for issues assigned to current user
{
"tool": "jira_search",
"arguments": {
"jql": "assignee = currentUser() AND status != Done",
"maxResults": 10
}
}
Get Issue Details
{
"tool": "jira_get_issue",
"arguments": {
"issueKey": "PROJ-123"
}
}
Create New Issue
{
"tool": "jira_create_issue",
"arguments": {
"project": "PROJ",
"issueType": "Task",
"summary": "New task summary",
"description": "Detailed description of the task",
"priority": "High"
}
}
Update Issue
{
"tool": "jira_update_issue",
"arguments": {
"issueKey": "PROJ-123",
"summary": "Updated summary",
"assignee": "user-account-id"
}
}
Add Comment
{
"tool": "jira_add_comment",
"arguments": {
"issueKey": "PROJ-123",
"comment": "This is a comment on the issue"
}
}
Logging
The MCP server maintains comprehensive logging:
- Log File:
mcp.log
(in current directory or system temp directory) - Log Levels: debug, info, warning, error
- Fallback: If file logging fails, logs to stderr
- Content: API requests, responses, errors, and tool executions
Error Handling
The server includes robust error handling:
- Missing Configuration: Graceful degradation with helpful error messages
- API Errors: Detailed logging of JIRA API response errors
- Network Issues: Proper timeout and retry handling
- File System: Automatic fallback for log file creation
Development
Project Structure
jira-mcp/
├── server.js # Main MCP server implementation
├── package.json # Node.js dependencies and scripts
├── .env.example # Environment variable template
├── .gitignore # Git ignore rules
├── README.md # This file
└── mcp.log # Log file (created at runtime)
Testing
Set your environment variables and test the server:
export JIRA_BASE_URL="https://your-jira-instance.com"
export JIRA_API_TOKEN="your-token-here"
# Test with npx
npx @hackdonalds/jira-mcp
# Or test from source
node server.js
API Compatibility
- Uses JIRA REST API v2 (
/rest/api/2/
) - Compatible with both Atlassian Cloud and Server installations
- Supports Bearer token authentication for modern JIRA instances
Troubleshooting
Common Issues
-
Authentication Errors (401)
- Verify your API token is correct and not expired
- Check that your JIRA instance supports Bearer token authentication
- Ensure JIRA_BASE_URL is correct and accessible
-
File System Errors (EROFS)
- The server automatically handles read-only file systems
- Logs will fall back to stderr if file logging fails
-
Empty Search Results
- Verify your JQL syntax is correct
- Check that you have permission to view the issues
- Try a simpler query like
project is not empty
-
Network/Timeout Issues
- Ensure your JIRA instance is accessible from your network
- Check for corporate firewalls or VPN requirements
Debug Mode
Enable verbose logging by setting:
export NODE_ENV=development
License
MIT License - see LICENSE file for details.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
Built with the Model Context Protocol TypeScript SDK.
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。