leave-management
Enables employees to check leave balance, apply for leave, and view leave history through natural language using Claude Desktop.
README
Leave Management MCP Server
An MCP (Model Context Protocol) server for employee leave management, built with FastMCP and Python.
Features
- Check leave balance — query remaining leave days for an employee
- Apply for leave — submit leave requests for specific dates
- View leave history — retrieve past leave records
- Greeting resource — personalized greeting endpoint
Prerequisites
- Python 3.14+
- uv — fast Python package manager
- Claude Desktop (to use the server with Claude)
Environment Setup
1. Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
Verify the installation:
uv --version
2. Clone the repository
git clone <your-repo-url>
cd mcp1_leave_management
3. Install Python 3.14
uv will read the .python-version file and auto-install the correct Python version:
uv python install
4. Create a virtual environment
uv venv
5. Activate the virtual environment
# macOS / Linux
source .venv/bin/activate
# Windows
.venv\Scripts\activate
6. Install the mcp dependency
uv add mcp
7. Verify the installation
python -c "from mcp.server.fastmcp import FastMCP; print('MCP installed successfully')"
Running the Server
Standalone (for testing)
python main.py
With MCP Inspector (interactive testing)
npx @modelcontextprotocol/inspector python main.py
Then open http://localhost:5173 in your browser to interact with the tools.
Connecting to Claude Desktop
1. Find your Claude Desktop config file
| OS | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
2. Add the server configuration
Open the config file and add an entry under mcpServers:
{
"mcpServers": {
"leave-management": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/mcp1_leave_management",
"python",
"main.py"
]
}
}
}
Replace /absolute/path/to/mcp1_leave_management with the actual path on your machine.
3. Restart Claude Desktop
Quit and relaunch Claude Desktop. The leave management tools will appear in the tool panel.
Available Tools
| Tool | Description | Parameters |
|---|---|---|
get_leave_balance |
Returns remaining leave days | employee_id: str |
apply_leave |
Applies leave for given dates | employee_id: str, leave_dates: List[str] |
get_leave_history |
Returns past leave dates | employee_id: str |
Example usage (in Claude)
Check leave balance for employee E001
Apply leave for E002 on 2025-06-10 and 2025-06-11
Show leave history for E001
Mock Data
The server starts with two pre-seeded employees:
| Employee ID | Initial Balance | Pre-existing Leaves |
|---|---|---|
| E001 | 18 days | 2024-12-25, 2025-01-01 |
| E002 | 20 days | None |
Data is held in memory and resets each time the server restarts.
Project Structure
mcp1_leave_management/
├── main.py # MCP server and tool definitions
├── pyproject.toml # Project metadata and dependencies
├── uv.lock # Locked dependency versions
├── .python-version # Pinned Python version (3.14)
└── README.md
Terminal setup steps from zero
uv venv --python 3.14 .venv
source .venv/bin/activate
which python
python --version
uv pip install mcp
uv
uv init
uv pip show mcp
uv run mcp install main.py
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。