employee-leave-management-mcp
Enables managing employee leave records through natural language, including adding employees, listing employees, adding/deleting leave entries, and viewing leave history.
README
Leave Management MCP Server
This project provides a simple MCP server for an employee leave-management system built with UV and Python.
Features
- Add employees
- List all employees
- Add leave entries for an employee
- List leave entries for an employee
- Delete leave entries
- Startup and tool logging for troubleshooting
Project structure
src/leave_management_mcp/server.py– MCP tool definitions and in-memory leave data storesrc/leave_management_mcp/__init__.py– package exports and entry pointtests/test_leave_management.py– regression tests for the core behaviorleave_management_mcp.log– runtime log file generated by the server
Run locally
From the project root:
cd C:\Users\VIJAY\Codebase\mcp\leave-management
uv run leave-management-mcp
The server uses stdio transport, which is the recommended transport for Claude Desktop.
Claude Desktop config
Create or edit this file:
%APPDATA%\Claude\claude_desktop_config.json
Use this exact config:
{
"mcpServers": {
"leave-management": {
"command": "C:\\Users\\VIJAY\\AppData\\Local\\Programs\\Python\\Python314\\Scripts\\uv.exe",
"args": [
"--directory",
"C:\\Users\\VIJAY\\Codebase\\mcp\\leave-management",
"run",
"leave-management-mcp"
]
}
}
}
Important:
- The earlier path
C:\Users\VIJAY\.local\bin\uv.exewas invalid on this machine. - The actual installed UV path is under the Python Scripts folder.
- Restart Claude Desktop after saving the file.
Example prompts in Claude
- "Add employee E001, Alice Johnson"
- "List all employees"
- "Add leave for E001 from 2026-08-20 to 2026-08-22 as annual"
- "Show leave records for E001"
- "Delete leave for E001 from 2026-08-20 to 2026-08-22"
Logging
The server writes logs to:
- stderr for immediate output
leave_management_mcp.login the project root for persisted troubleshooting
This helps confirm whether the MCP server is starting correctly when Claude Desktop launches it.
Validation
Run the test suite:
cd C:\Users\VIJAY\Codebase\mcp\leave-management
uv run pytest -q
Verified result:
2 passed in 2.85s
The project passes the current regression tests and the server launch path has been verified.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.