Jira MCP Server

Jira MCP Server

Integrates with Jira Cloud to enable comprehensive issue management, project tracking, and team collaboration through natural language, including creating/updating tickets, searching with JQL, managing workflows, and adding comments.

Category
访问服务器

README

Jira MCP Server 🎫

A Model Context Protocol (MCP) server that integrates with Jira Cloud to provide comprehensive issue management, project tracking, and team collaboration capabilities directly through Claude and other MCP clients.

Features ✨

Issue Management

  • Search Issues: Advanced JQL-based searching with simple filters
  • Get Issue Details: Comprehensive issue information with comments
  • Create Issues: Create Stories, Bugs, Tasks, and other issue types
  • Update Issues: Change status, assignee, priority, and summary
  • Add Comments: Add comments to existing issues
  • My Issues: Quick access to your assigned tickets

Project Management

  • List Projects: View all accessible projects
  • Project Details: Get comprehensive project information
  • Issue Types: See available issue types per project

Smart Features

  • Flexible User Assignment: Use 'me', 'myself', or actual usernames/emails
  • Status Transitions: Automatically handle Jira workflow transitions
  • Rich Text Support: Handles Atlassian Document Format (ADF)
  • Error Handling: Comprehensive error messages and validation

Quick Start 🚀

1. Prerequisites

  • Python 3.10 or higher
  • Claude Desktop - Download and install from claude.ai/download
  • Access to a Jira Cloud instance
  • Jira API token (we'll generate this below)

2. Installation

# Clone this repository
git clone https://github.com/jondoesflow/MCP_Server_JIra.git
cd MCP_Server_JIra

# Install uv (Python package manager) if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env

# Set up virtual environment and install dependencies
$HOME/.local/bin/uv venv
$HOME/.local/bin/uv add "mcp[cli]" httpx python-dotenv

3. Jira API Setup

  1. Generate an API Token:

    • Go to Atlassian Account Security
    • Click "Create API token"
    • Give it a name (e.g., "MCP Server")
    • Copy the generated token (save it somewhere safe!)
  2. Create Environment Configuration:

    # Copy the example environment file
    cp .env.example .env
    
  3. Edit the .env file: Open the .env file in your text editor and fill in your actual values:

    # Your Jira Cloud instance URL (without trailing slash)
    JIRA_BASE_URL=https://yourcompany.atlassian.net
    
    # Your Jira account email
    JIRA_EMAIL=your.email@company.com
    
    # Your Jira API token (paste the token you generated above)
    JIRA_API_TOKEN=your_actual_api_token_here
    

    Important: Replace the placeholder values with your actual Jira details!

4. Test Your Connection

# Test your Jira connection before proceeding
$HOME/.local/bin/uv run test_connection.py

This should show:

  • ✅ Successful login to your Jira instance
  • ✅ List of accessible projects
  • ✅ Ability to search for issues

If any tests fail, double-check your .env file values.

5. Configure Claude Desktop

  1. Create the Claude Desktop configuration file:

    macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

  2. Add this configuration (replace /ABSOLUTE/PATH/TO/ with your actual path):

    {
      "mcpServers": {
        "jira": {
          "command": "/Users/yourusername/.local/bin/uv",
          "args": [
            "--directory",
            "/ABSOLUTE/PATH/TO/MCP_Server_JIra",
            "run",
            "jira_server.py"
          ]
        }
      }
    }
    

    To find your absolute path, run this in the project directory:

    pwd
    
  3. Example configuration (update the username and path):

    {
      "mcpServers": {
        "jira": {
          "command": "/Users/jonathanrussell/.local/bin/uv",
          "args": [
            "--directory",
            "/Users/jonathanrussell/Documents/VIbe/MCP/MCP_Server_JIra",
            "run",
            "jira_server.py"
          ]
        }
      }
    }
    

6. Restart Claude Desktop

Important: Completely quit and restart Claude Desktop for the changes to take effect. You should then see MCP tools available in the interface.

Usage Examples 💡

Search for Issues

"Show me all high priority bugs in the MOBILE project"
"Find issues assigned to me that are in progress"
"Search for issues with 'login' in the title"

Create Issues

"Create a bug report for the login timeout issue in project WEB"
"Create a story for implementing dark mode, assign it to me"
"Create a task to update documentation with high priority"

Manage Issues

"Move ticket WEB-123 to In Progress"
"Assign ticket MOBILE-456 to john.doe@company.com"
"Add a comment to WEB-123 saying 'Fixed in latest build'"

Project Information

"List all available projects"
"Show me details about the MOBILE project"
"What are my current assigned issues?"

Available Tools 🛠️

Tool Description
search_issues Search issues with JQL or simple filters
get_issue Get detailed information about a specific issue
get_my_issues Get issues assigned to you
create_issue Create new issues (Stories, Bugs, Tasks)
update_issue Update issue status, assignee, priority, summary
add_comment Add comments to issues
list_projects List all accessible projects
get_project_info Get detailed project information

Configuration Options ⚙️

Environment Variables

Variable Description Required
JIRA_BASE_URL Your Jira Cloud URL (e.g., https://company.atlassian.net) Yes
JIRA_EMAIL Your Jira account email Yes
JIRA_API_TOKEN Your Jira API token Yes

JQL Examples

The server supports full JQL (Jira Query Language) for advanced searching:

project = "WEB" AND assignee = currentUser() AND status != Done
priority in (High, Highest) AND created >= -7d
issuetype = Bug AND status = "In Progress"
text ~ "login" AND project in (WEB, MOBILE)

Troubleshooting 🔧

Common Issues

  1. "Missing required environment variables"

    • Ensure your .env file exists and contains all required variables
    • Check that variable names match exactly (case-sensitive)
  2. "Jira API error: 401"

    • Verify your email and API token are correct
    • Ensure the API token hasn't expired
    • Check that your Jira URL is correct (no trailing slash)
  3. "User not found" when assigning

    • Use exact email addresses or usernames
    • Try using 'me' to assign to yourself
    • Verify the user has access to the project
  4. "Status not available" when updating

    • Check available transitions with the error message
    • Jira workflows restrict which status changes are allowed
    • Use exact status names (case-sensitive)

Debug Mode

To enable detailed logging, modify the logging level in jira_server.py:

logging.basicConfig(level=logging.DEBUG)

Testing API Connection

You can test your Jira connection independently:

# Test API connection
curl -u "your.email@company.com:your_api_token" \
  -H "Accept: application/json" \
  "https://yourcompany.atlassian.net/rest/api/3/myself"

Security Notes 🔒

  • API Tokens: Never commit your .env file to version control
  • Permissions: The server respects your Jira permissions - you can only access what you normally can
  • Rate Limiting: The server includes basic rate limiting respect for Jira's API limits
  • HTTPS Only: Always use HTTPS Jira URLs for secure communication

Contributing 🤝

This MCP server is designed to be extensible. To add new features:

  1. Add new tool functions using the @mcp.tool() decorator
  2. Follow the existing error handling patterns
  3. Update this README with new functionality
  4. Test thoroughly with your Jira instance

License 📄

This project is open source. Feel free to modify and distribute according to your needs.


Need Help? Check the MCP Documentation or Jira REST API Documentation.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选