Leave Management MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Leave Management MCP Server Show leave balance for E001"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Leave Management MCP Server
An AI-powered Leave Management System built using the Model Context Protocol (MCP).
This project demonstrates how a Large Language Model (LLM) can discover and invoke MCP tools to perform business operations such as checking leave balances, applying for leave, and retrieving leave history through natural language.
Features
Built using the FastMCP framework
Streamlit-based AI client
Gemini API for intelligent tool selection
SQLite database for persistent data storage
Dynamic MCP tool discovery using
list_tools()Natural language interface
Related MCP server: leave-manager-mcp
Project Structure
.
├── app.py # Streamlit AI Client
├── main.py # MCP Server
├── llm.py # Gemini Integration
├── database.py # SQLite Helper Functions
├── init_db.py # Database Initialization
├── pyproject.toml
├── uv.lock
├── .python-version
├── .env.example
├── README.md
└── .gitignoreAvailable MCP Tools
get_leave_balanceapply_leaveget_leave_history
Tech Stack
Python
Model Context Protocol (MCP)
FastMCP
Streamlit
Gemini API
SQLite
uv
Installation
1. Clone the repository
git clone https://github.com/ratankumarthakur/leave-management-mcp
cd leave-management-mcp2. Install dependencies
uv sync3. Configure the environment
Create a .env file in the project root.
GEMINI_API_KEY=YOUR_API_KEY4. Initialize the database
python init_db.py5. Run the application
streamlit run app.pyExample Queries
Try asking:
Show leave balance for E001
Apply leave for E002 on 2026-08-10
Show leave history for E001
Apply leave for E001 on 15 September 2026
Architecture
User
│
▼
Streamlit Client
│
▼
Gemini LLM
│
▼
MCP Client
│
▼
MCP Server
│
▼
SQLite DatabaseHow It Works
The user enters a natural language query.
The Gemini model selects the appropriate MCP tool.
The Streamlit client invokes the selected MCP tool.
The MCP server executes the requested operation.
Data is read from or written to the SQLite database.
The result is returned to the client and displayed to the user.
Learning Objective
This project was built to understand the fundamentals of the Model Context Protocol (MCP), including:
Building an MCP server
Creating an MCP client
Dynamic tool discovery
LLM-driven tool invocation
Database-backed tool execution
Developing an AI-powered application using Streamlit
Screenshot
Available Tools
3 toolsapply_leaveD
Inputs: employee_id (required), leave_dates (required). Returns: result
get_leave_balanceD
Inputs: employee_id (required). Returns: result
get_leave_historyD
Inputs: employee_id (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool covers a distinct aspect: balance inquiry, leave application, and history lookup. There is no overlap or ambiguity between them.
All tool names follow the consistent verb_noun pattern: get_leave_balance, apply_leave, get_leave_history. The naming is clear and predictable.
Three tools are well-scoped for a simple leave management server, covering the core employee-facing actions without unnecessary bloat.
Core leave lifecycle is covered (check balance, apply, view history), but missing operations like cancel or update leave applications are notable gaps.
Maintenance
Related MCP Connectors
Employee leave and PTO: requests, approvals, balances, who is out, and conflict checks.
Track and manage employee time off with quick balance lookups and streamlined applications. Find t…
CharlieHR MCP server for ChatGPT, Claude and any AI agent: list team members, list time off requests, approve time off request, deny time off request, book time off, record sick day, adjust time off allowance and cancel time off booking in your own CharlieHR account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to CharlieHR yourself; Cotlet does not store your password and you need no CharlieHR API key. About the official CharlieHR API: CharlieHR has an API, but a narrow one, and no official MCP server (checked 20 Oct 2026). A Super Admin creates a Client ID and Client Secret under Company > Integrations > API Access; the API covers team members, leave, offices and teams. Setup and FAQ: https://cotlet.dev/integrations/charliehr-api-mcp-server
HONO HRMS in plain language: apply leave, check attendance and ask HR policy questions.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables employees to check leave balance, apply for leave, and view leave history through natural language using Claude Desktop.-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage employee leave by checking balances, applying for leave, and viewing history via MCP tools.-
- FlicenseNot gradedqualityDmaintenanceEnables natural-language-based employee leave management including leave balance checks, leave applications, approvals, and history retrieval through an MCP-compatible client.-
- FlicenseBqualityDmaintenanceEnables LLMs to manage employee leave by checking balances, applying for leave, and viewing history.3-