hr-assistant
Enables local employee onboarding, leave tracking, meeting coordination, and workplace requests through any MCP-compatible client, with optional SMTP notifications.
README
HR Assistant MCP Server
A practical local HR assistant for employee onboarding, leave tracking, meeting coordination, and workplace requests. It connects to any MCP-compatible client and runs without a database or paid service.
System design

The MCP server is the single entry point for HR workflows. Employee, leave, meeting, and request features are separate modules, while email delivery stays optional. Data is stored locally in memory for a fast demo experience.
Highlights
- Onboard employees with a single tool call.
- Maintain an employee directory with manager and direct-report relationships.
- Check leave balances, submit leave dates, and review leave history.
- Schedule, list, and cancel orientation or HR meetings.
- Create and update laptop, headset, access-badge, and other workplace requests.
- Send notifications through SMTP when credentials are configured locally.
- Start with deterministic sample employees for immediate testing.
Getting started
Requirements: Python 3.10 or later.
git clone https://github.com/sarthak-here/hr-assistant-mcp.git
cd hr-assistant-mcp
python -m pip install -e ".[test]"
python server.py
The server communicates through standard input/output, which is what MCP clients expect. It will not display an interactive chat prompt when launched directly.
Run the test suite whenever you make changes:
python -m pytest
Add to an MCP client
Use an absolute path to the cloned project in your client configuration.
{
"mcpServers": {
"hr-assistant": {
"command": "python",
"args": ["C:\\path\\to\\hr-assistant-mcp\\server.py"]
}
}
}
After connecting, try one of these requests:
Show the current employee directory.
Onboard Priya Shah as a Product Analyst reporting to EMP-002.
Check the leave balance for EMP-003.
Create a monitor request for EMP-004.
Main tools
| Area | Tools |
|---|---|
| Employee directory | create_employee, find_employees, get_employee, get_direct_reports |
| Leave | get_leave_balance, apply_leave, get_leave_history |
| Meetings | schedule_meeting, list_meetings, cancel_meeting |
| Workplace requests | create_equipment_request, update_request_status, list_requests |
| Onboarding | onboard_employee |
| Notifications | send_notification |
onboard_employee creates the employee record, leave account, and the standard laptop, headset, and access-badge requests together. Schedule orientation separately once a time is confirmed.
Email setup
Email is optional. Copy .env.example to .env, then fill in the SMTP values if you want to use send_notification.
Copy-Item .env.example .env
The .env file is ignored by Git. All other HR features work without email configuration.
Project files
hr-assistant-mcp/
assets/ Hand-drawn system-design image
peopleops/ Domain models and HR workflow managers
tests/ Automated checks
server.py MCP tools
emails.py Optional SMTP notifications
.env.example Safe configuration template
pyproject.toml Project dependencies and test settings
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。