Jira 9.12.14 MCP Server
Enables AI models to search Jira issues using JQL and retrieve issue details through the Jira 9.12.14 API.
README
Jira 9.12.14 MCP Server
This is a Model Context Protocol (MCP) server implementation for the Jira 9.12.14 API. It allows AI models like Claude to securely interact with Jira through well-defined tools.
Features
- JQL Search: Execute JQL queries to find issues in Jira
- Get Issue: Retrieve detailed information about a specific issue by ID or key
Prerequisites
- Node.js (v16 or higher)
- npm or yarn
- A Jira instance
- Authentication credentials for Jira API
Installation
Option 1: Using npx (Recommended)
The easiest way to use this MCP server is with npx:
# Create a directory for your configuration
mkdir jira-mcp && cd jira-mcp
# Create .env file with your credentials
cat > .env << EOL
JIRA_API_URL=https://your-domain.atlassian.net
JIRA_AUTH_TOKEN=your-token-here
EOL
# Run the server directly
npx @andrewyun/jira-9-12-14-mcp-server
Option 2: Manual Installation
- Clone the repository
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
Option 1: Environment Variables in .env File
The server reads configuration from a .env file in the current directory. Create a file named .env with the following settings:
JIRA_API_URL=https://your-domain.atlassian.net
JIRA_AUTH_TOKEN=your-jira-token
You must create this file in the directory where you run the server.
Option 2: MCP JSON Environment Variables
As an alternative to the .env file, you can configure the server using MCP JSON environment variables. Update your Claude for Desktop configuration in the mcpServers section:
{
"mcpServers": {
"jira": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/jira-9.12.14-mcp-server/dist/index.js"
],
"env": {
"MCP_JIRA_API_URL": "https://your-domain.atlassian.net",
"MCP_JIRA_AUTH_TOKEN": "your-jira-token"
}
}
}
}
Using the MCP JSON environment variables means you don't need to create a .env file.
Environment Variable Details
JIRA_API_URLorMCP_JIRA_API_URL: The base URL of your Jira instance (e.g.,https://your-domain.atlassian.net)JIRA_AUTH_TOKENorMCP_JIRA_AUTH_TOKEN: Your Jira API token or Personal Access Token (PAT)
Getting a Jira API Token
- Log in to your Atlassian account
- Go to Account Settings > Security > Create and manage API tokens
- Click "Create API token"
- Give it a name like "MCP Server"
- Copy the generated token to your
.envfile or MCP JSON configuration
Usage
Running the server
npm start
Integration with Claude for Desktop
- Open your Claude for Desktop App configuration at
~/Library/Application Support/Claude/claude_desktop_config.json(MacOS) or%AppData%\Claude\claude_desktop_config.json(Windows) - Add the server configuration:
{
"mcpServers": {
"jira": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/jira-9.12.14-mcp-server/dist/index.js"
],
"env": {
"MCP_JIRA_API_URL": "https://your-domain.atlassian.net",
"MCP_JIRA_AUTH_TOKEN": "your-jira-token"
}
}
}
}
Replace /ABSOLUTE/PATH/TO/ with the actual path to the server on your system.
Using With npx
If you installed via npx, your Claude configuration would look like:
{
"mcpServers": {
"jira": {
"command": "npx",
"args": [
"--yes",
"@andrewyun/jira-9-12-14-mcp-server"
],
"env": {
"MCP_JIRA_API_URL": "https://your-domain.atlassian.net",
"MCP_JIRA_AUTH_TOKEN": "your-jira-token"
}
}
}
}
Important: If you're using the MCP JSON environment variables, you don't need a .env file. If you're not using MCP JSON environment variables, make sure you have a .env file in your home directory or in the directory where Claude for Desktop is installed when using npx.
Available Tools
JQL Search (mcp_jira_jql_search)
Executes JQL queries to find issues in Jira.
Parameters:
jql(required): JQL query stringfields(optional): List of fields to return for each issuemaxResults(optional): Maximum number of results to returnstartAt(optional): Index of the first result to returnexpand(optional): Additional information to include in the response
Get Issue (mcp_jira_get_issue)
Retrieves detailed information about a specific issue by ID or key.
Parameters:
issueIdOrKey(required): ID or key of the issuefields(optional): List of fields to include in the responseexpand(optional): Additional information to include in the responseproperties(optional): Properties to include in the responsefailFast(optional): Whether to fail quickly on errors (default: false)
Troubleshooting
If you see errors like JIRA_API_URL environment variable is required, make sure you:
- Have created a
.envfile in the directory where you're running the server, OR - Have provided
MCP_JIRA_API_URLandMCP_JIRA_AUTH_TOKENin your Claude for Desktop configuration MIT
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。