jira-cli-mcp
MCP server that wraps the jira-cli command-line tool to enable AI assistants to interact with Jira.
README
Jira CLI MCP Server
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
-
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 -
Install jira-cli-mcp:
brew tap choplin/jira-cli-mcp brew install jira-cli-mcp -
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)
- Download the binary for your platform from releases
- 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
- Add to config:
{
"mcpServers": {
"jira-cli": {
"command": "jira-cli-mcp"
}
}
}
Option 4: Build from Source
- Clone and run directly:
git clone https://github.com/choplin/jira-cli-mcp.git
cd jira-cli-mcp
bun install
- 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:
-
First install jira-cli-mcp using one of the methods in the Installation section
-
Create a
.claude/mcp.jsonfile in your project root:
{
"servers": {
"jira-cli": {
"command": "jira-cli-mcp"
}
}
}
- 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+):
-
First install jira-cli-mcp using one of the methods in the Installation section
-
Create
.vscode/mcp.jsonin your repository:
{
"servers": {
"jira-cli": {
"command": "jira-cli-mcp"
}
}
}
-
Open the
.vscode/mcp.jsonfile in VS Code and click the [Start] button to activate the server -
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 implementationssrc/utils/- Shared utilities and typestests/- Unit tests with mocked jira-clitests/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
-
"jira-cli not found" error
- Ensure jira-cli is installed:
which jira - If using a custom path, set
JIRA_CLI_PATHenvironment variable
- Ensure jira-cli is installed:
-
Authentication errors
- Run
jira meto verify authentication - Re-authenticate with
jira initif needed
- Run
-
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
-
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
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。