📅 Leave Manager MCP Server

A modern model context protocol (MCP) server built with FastMCP in Python for managing employee leave balances and history. It allows LLMs to query leave balances, submit leave applications, and view leave history for employees.

---

📂 Project Structure

To maintain clean modularity and scale features independently, tools and resources are separated:

• [server.py](file:///d:/practice/Mcp-server/first-mcp-server/server.py): Instantiates the FastMCP server object.
• [tools/](file:///d:/practice/Mcp-server/first-mcp-server/tools): Package directory holding all server tools.
  • [leave_tools.py](file:///d:/practice/Mcp-server/first-mcp-server/tools/leave_tools.py): Defines MCP tools (get_leave_balance, apply_leave, get_leave_history).
• [resources/](file:///d:/practice/Mcp-server/first-mcp-server/resources): Package directory holding all server resources.
  • [greeting_resources.py](file:///d:/practice/Mcp-server/first-mcp-server/resources/greeting_resources.py): Defines MCP resources.
• [main.py](file:///d:/practice/Mcp-server/first-mcp-server/main.py): Entrypoint file which registers the tools and resources, and launches the server.

---

🛠️ Features & API Surface

This MCP server exposes the following tools and resources to LLMs:

Tools

• get_leave_balance(employee_id: str): Checks how many leave days are remaining for the given employee (e.g., "E001").
• apply_leave(employee_id: str, leave_dates: list[str]): Submits a leave request for specific dates (e.g., ["2025-04-17", "2025-05-01"]). Validates leave balance and updates the mock database.
• get_leave_history(employee_id: str): Fetches the log of past leave dates for the employee.

Resources

• greeting://{name}: A personalized greeting resource that provides instructions on how to use the server.

---

📋 Prerequisites

Before setting up the project, make sure you have the following installed:

1. Python (version 3.13 or higher)
2. uv - An extremely fast Python package manager and resolver.
   • Windows (PowerShell):

     powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
     

   • macOS/Linux:

     curl -LsSf https://astral.sh/uv/install.sh | sh
     

3. Claude Desktop (optional, for testing the desktop application integration)

---

🚀 Setup & Usage

1. Install Dependencies

The project uses uv to manage dependencies. Run the following command to add and install required dependencies:

uv add mcp[cli]

2. Run the MCP Server

You have three ways to run and test the server:

A. Basic Run

To run the server directly via standard Python (for testing basic initialization):

uv run python main.py

B. Development & Local Testing (MCP Inspector)

The recommended way to test and debug your tools locally is using the MCP Inspector:

uv run mcp dev main.py

This command starts the server and spins up the web-based MCP Inspector. You can use it to view, call, and debug your tools/resources in a browser UI.

C. Installation into Claude Desktop

To integrate this server directly with your Claude Desktop client:

1. Ensure Claude Desktop is installed and you've switched it to Developer Mode.
2. Run the following installation helper command:

uv run mcp install main.py

This automatically locates your Claude Desktop MCP configuration file and adds this server setup. 3. Open or restart Claude Desktop. 4. Click the + (plus) icon/selector in the chat window. You should see LeaveManager listed as an active connector. Claude will now query the server automatically to answer your leave management questions!

---

📊 Mock Database

The project contains pre-configured mock data for employees (E001 to E010) located in [employeeLeaveData.py](file:///d:/practice/Mcp-server/first-mcp-server/mock_data/employeeLeaveData.py).

Example Employee records:

• E001: 18 leave days remaining.
• E002: 20 leave days remaining.
• E003: 16 leave days remaining.