jira-cli-mcp

jira-cli-mcp

MCP server that wraps the jira-cli command-line tool to enable AI assistants to interact with Jira.

Category
访问服务器

README

Jira CLI MCP Server

CI License: MIT MCP

MCP (Model Context Protocol) server that wraps the jira-cli command-line tool to enable AI assistants to interact with Jira.

Why jira-cli-mcp?

If you're looking for a Jira MCP server, here's what makes jira-cli-mcp unique:

  • 🚀 Leverage Existing Tools - Works seamlessly with your existing jira-cli setup and authentication
  • 🔒 Security-First - No API tokens in config files; authentication handled by jira-cli
  • 🪶 Lightweight - Just a Bun process, no Docker or containers required

When to use mcp-atlassian instead?

Choose mcp-atlassian if you:

  • Need Confluence support (we're Jira-only)
  • Prefer Docker deployment
  • Want a self-contained solution without CLI dependencies
  • Need direct API integration rather than CLI wrapping

Features

  • create_ticket - Create new Jira tickets with customizable fields
  • list_tickets - Search and list Jira tickets using JQL queries
  • get_ticket - Get detailed ticket information including comments
  • update_ticket_description - Update ticket descriptions with rich text formatting
  • add_comment - Add comments to tickets with Markdown support
  • assign_to_me - Assign tickets to the current user
  • move_ticket - Move tickets between different statuses
  • open_ticket_in_browser - Open a Jira ticket in the default web browser

Quick Start

  1. Install and configure jira-cli (Installation guide):

    # Install jira-cli (macOS)
    brew install ankitpokhrel/jira-cli/jira-cli
    
    # Configure jira-cli with your Jira instance
    jira init
    
  2. Install jira-cli-mcp:

    brew tap choplin/jira-cli-mcp
    brew install jira-cli-mcp
    
  3. Add to Claude Desktop config (see Setup below)

Prerequisites

  • jira-cli installed and authenticated
  • Bun runtime (only needed for development or if installing from source)

Installation

Option 1: Install via Homebrew (macOS/Linux)

brew tap choplin/jira-cli-mcp
brew install jira-cli-mcp

Option 2: Install via npm

# Install globally with npm
npm install -g @choplin/jira-cli-mcp

# Or with Bun
bun install -g @choplin/jira-cli-mcp

Option 3: Download Binary

Download the pre-compiled binary for your platform from the releases page:

  • macOS (Apple Silicon): jira-cli-mcp-darwin-arm64.tar.gz
  • macOS (Intel): jira-cli-mcp-darwin-x64.tar.gz
  • Linux (x64): jira-cli-mcp-linux-x64.tar.gz
  • Linux (ARM64): jira-cli-mcp-linux-arm64.tar.gz
# Example for macOS (Apple Silicon)
tar -xzf jira-cli-mcp-darwin-arm64.tar.gz
chmod +x jira-cli-mcp-darwin-arm64
sudo mv jira-cli-mcp-darwin-arm64 /usr/local/bin/jira-cli-mcp

Option 4: Build from Source

git clone https://github.com/choplin/jira-cli-mcp.git
cd jira-cli-mcp
bun install
bun run build:prod

Setup for Claude Desktop

Option 1: Using Homebrew Installation (Recommended)

If you installed via Homebrew (as shown in Quick Start), add to your claude_desktop_config.json:

{
  "mcpServers": {
    "jira-cli": {
      "command": "jira-cli-mcp"
    }
  }
}

Option 2: Using npm Package

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "jira-cli": {
      "command": "npx",
      "args": ["@choplin/jira-cli-mcp"]
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "jira-cli": {
      "command": "jira-cli-mcp"
    }
  }
}

Option 3: Using Pre-compiled Binary (No Dependencies)

  1. Download the binary for your platform from releases
  2. Extract and move to your PATH:
tar -xzf jira-cli-mcp-darwin-arm64.tar.gz
sudo mv jira-cli-mcp-darwin-arm64 /usr/local/bin/jira-cli-mcp
  1. Add to config:
{
  "mcpServers": {
    "jira-cli": {
      "command": "jira-cli-mcp"
    }
  }
}

Option 4: Build from Source

  1. Clone and run directly:
git clone https://github.com/choplin/jira-cli-mcp.git
cd jira-cli-mcp
bun install
  1. Add to config:
{
  "mcpServers": {
    "jira-cli": {
      "command": "bun",
      "args": ["run", "/path/to/jira-cli-mcp/src/index.ts"]
    }
  }
}

Configuration Location

The config file is typically located at:

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

Verification

After setup, restart Claude Desktop and check if the MCP server is loaded by asking Claude about available Jira tools.

Setup for Other AI Assistants

Claude Code

Claude Code has built-in support for MCP servers. To use jira-cli-mcp in your project:

  1. First install jira-cli-mcp using one of the methods in the Installation section

  2. Create a .claude/mcp.json file in your project root:

{
  "servers": {
    "jira-cli": {
      "command": "jira-cli-mcp"
    }
  }
}
  1. Restart Claude Code and the MCP server will be automatically loaded

You can then use Jira commands directly in your conversation, such as:

  • "List my open Jira tickets"
  • "Show me details for PROJ-123"
  • "Add a comment to PROJ-456"

GitHub Copilot (VS Code)

GitHub Copilot supports MCP servers in Visual Studio Code (version 1.99+):

  1. First install jira-cli-mcp using one of the methods in the Installation section

  2. Create .vscode/mcp.json in your repository:

{
  "servers": {
    "jira-cli": {
      "command": "jira-cli-mcp"
    }
  }
}
  1. Open the .vscode/mcp.json file in VS Code and click the [Start] button to activate the server

  2. In Copilot Chat:

    • Open Copilot Chat panel
    • Select "Agent" from the popup menu
    • Click the tools icon to see available MCP servers

Note: MCP support in GitHub Copilot is currently in public preview.

Development

Running Tests

# Run unit tests only
bun test

# Run all tests including integration tests
bun run test:integration

# Run integration tests with a specific test ticket
JIRA_CLI_MCP_TEST_TICKET=PROJ-123 bun run test:integration

Environment Variables

  • JIRA_CLI_PATH - Custom path to jira-cli executable (default: "jira")

Development Environment Variables

  • JIRA_CLI_MCP_TEST_TICKET - Ticket key for integration tests (required for non-listing integration tests)
  • INTEGRATION_TEST=true - Enable integration tests

Type Checking

bun run typecheck

Linting and Formatting

bun run lint
bun run format

Architecture

  • src/tools/ - MCP tool implementations
  • src/utils/ - Shared utilities and types
  • tests/ - Unit tests with mocked jira-cli
  • tests/integration/ - Integration tests with real jira-cli

Notes

  • The server uses Atlassian Document Format (ADF) for rich text handling
  • Markdown input is automatically converted to ADF by jira-cli
  • All integration tests require proper jira-cli authentication

Troubleshooting

Common Issues

  1. "jira-cli not found" error

    • Ensure jira-cli is installed: which jira
    • If using a custom path, set JIRA_CLI_PATH environment variable
  2. Authentication errors

    • Run jira me to verify authentication
    • Re-authenticate with jira init if needed
  3. MCP server not showing in Claude Desktop

    • Verify the config file path is correct
    • Ensure the path in config uses absolute paths, not relative
    • Restart Claude Desktop after config changes
  4. Permission errors on macOS

    • Grant terminal/Claude Desktop full disk access in System Preferences
    • Ensure jira-cli has necessary permissions

Debug Mode

To see detailed logs, you can run the server manually:

cd /path/to/jira-cli-mcp
bun run src/index.ts

License

This project is licensed under the MIT License - see the LICENSE file for details.

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