Jira MCP Server
Provides read-only issue and project management tools for Jira Server/DC, enabling querying issues, projects, and assignments via natural language.
README
Jira MCP Server
This is a simple prototype of a Jira Server/DC MCP server. It uses Python APIs for Jira documented here, and the MCP Python SDK.
Run steps
- Copy .env.example to .env, and replace
YOUR_JIRA_HOST_URLandYOUR_JIRA_PERSONAL_ACCESS_TOKEN. The Jira host url must belong to a Jira server/ DC (the project is intended for Jira server/ DC). To generate your Personal Access Token, refer the section 'Creating PATs in the application' here. - Create and activate virtual environment, and install dependencies -
pip install -r requirements.txt - Run
mcp dev jira_mcp_server.py- this runs MCP Inspector which is a local way to test the defined tools and responses without involving an LLM.
MCP Integration
The server can be started using python jira_mcp_server.py.
- With Claude Desktop - Add to your claude_desktop_config.json the command and args :
{
"mcpServers": {
"jira": {
"command": "/Users/harshal.mittal/.pyenv/versions/3.10.0/bin/python",
"args": [
"/Users/harshal.mittal/projects/jira-mcp-server/jira_mcp_server.py"
]
}
}
}
Include the full paths of the python binary and the jira_mcp_server.py file on your system (reference).
- With Other MCP Clients - The server follows the standard MCP protocol and works with any MCP-compatible client.
Project Structure
JiraMCPserver/
├── jira_client/
│ ├── __init__.py
│ │── client.py
| |── issue.py
| └── project.py
├── models/
│ ├── __init__.py
│ │── constants.py
| └── issue.py
├── jira_mcp_server.py
├── .env.example
├── .gitignore
└── requirements.txt
Supported operations -
This currently supports read-only issue and project management tools, for example
- "Give me all issues which are related to Recovery and open for more than 90 days"
- "List all issues assigned to Harshal Mittal resolved in last 30 days"
- "Find count of all open issues in ENG project"
Tools for write/ updating Jira can be added in similar way.
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。