HRMS MCP Server
An MCP server for HR management that enables adding employees, managing tickets and leaves, sending emails, and onboarding new hires via in-memory mock data.
README
HR Management System (MCP Server)
⚠️ Work in progress. This project is still under active development and is not production-ready. The manager functions in
HRMS/are mock implementations that mimic the API calls of Keka HR software, using in-memory sample data instead of real Keka API integration.
An HR assistant exposed as an MCP (Model Context Protocol) server. It lets an MCP-compatible client (e.g. Claude Desktop) manage employees, tickets, leaves, and meetings, and send emails — backed by in-memory data that is seeded with sample employees on startup.
Features
The MCP server (server.py) exposes the following tools and prompt:
| Tool | Description |
|---|---|
add_employee |
Add a new employee to the HRMS. |
get_employee_details |
Look up an employee's details by name. |
create_ticket |
Raise a ticket for equipment/items (laptop, ID card, etc.). |
update_ticket_status |
Update a ticket's status. |
list_tickets |
List tickets for an employee, optionally filtered by status. |
send_email |
Send an email via SMTP. |
| Prompt | Description |
|---|---|
onboard_new_employee |
Guided workflow to onboard a new hire end-to-end. |
Additional domain logic lives in the HRMS/ package (employee, leave, meeting,
and ticket managers plus Pydantic schemas.py). These managers currently mock
Keka's HR API; sample data is loaded by utils.seed_services on server start.
Requirements
- Python >= 3.12
- uv (recommended) for dependency management
Setup
-
Clone the repository:
git clone <your-repo-url> cd HR_Management_System -
Install dependencies:
uv sync -
Configure environment variables. Copy the example file and fill in your SMTP credentials:
cp .env.example .envVariable Description MS_EMAILSender email address / SMTP login. MS_EMAIL_PWDSMTP password or app password. For Gmail, generate an App Password rather than using your account password.
Running
Start the MCP server (uses stdio transport):
uv run server.py
To use it with an MCP client such as Claude Desktop, add an entry to the client's MCP server configuration pointing at this command, for example:
{
"mcpServers": {
"atliq-hr-assist": {
"command": "uv",
"args": ["run", "server.py"],
"cwd": "/absolute/path/to/HR_Management_System"
}
}
}
You can also test the email sender directly:
uv run emails.py
Project structure
.
├── server.py # MCP server entry point (tools & prompts)
├── emails.py # SMTP email sender
├── utils.py # Seeds the managers with sample data
├── main.py # Hello-world placeholder
├── HRMS/ # Core domain package (mocks Keka HR API)
│ ├── employee_manager.py
│ ├── leave_manager.py
│ ├── meeting_manager.py
│ ├── ticket_manager.py
│ └── schemas.py # Pydantic models
├── .env.example # Template for required environment variables
└── pyproject.toml
Roadmap / TODO
- Replace the mock
HRMS/managers with real Keka HR API integration. - Persist data instead of using in-memory seeded sample data.
- Expand MCP tool coverage for leave and meeting management.
Notes
- Data is stored in memory and re-seeded on every start; it is not persisted.
- Never commit your
.envfile — it contains secrets and is git-ignored.
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。