atliq-hrms-assist

atliq-hrms-assist

An MCP server that enables AI assistants to manage HR operations like employee onboarding, leave requests, meeting scheduling, and equipment tickets through natural language.

Category
访问服务器

README

🏢 Atliq HRMS Assist — MCP Server

An AI-powered Human Resource Management System (HRMS) built as a Model Context Protocol (MCP) server. It connects directly to Claude Desktop, allowing you to manage employees, leaves, meetings, tickets, and emails using natural language.


📋 Table of Contents


🌟 Overview

Atliq HRMS Assist is an MCP server that exposes HR management capabilities as tools and prompts for AI assistants. Built with FastMCP and Pydantic, it enables Claude to perform real HR operations — from onboarding employees to scheduling meetings — all through natural language.


✨ Features

Category Capability
👤 Employee Management Add employees, search by name, get details
🌴 Leave Management Check balances, apply leaves, view history
📅 Meeting Scheduler Schedule, view, and cancel meetings
🎫 Ticket System Create and update equipment/IT request tickets
📧 Email Notifications Send welcome emails, meeting invites, leave confirmations
🤖 AI Prompts Pre-built prompts for onboarding, leave, and meeting workflows

📁 Project Structure

atliq-hrms-assist/
├── HRMS/
│   ├── __init__.py          # Exports all managers and schemas
│   ├── employee_manager.py  # Employee CRUD and search
│   ├── leave_manager.py     # Leave balance and application
│   ├── meeting_manager.py   # Meeting scheduling and cancellation
│   ├── ticket_manager.py    # Equipment/IT ticket management
│   └── schemas.py           # Pydantic data models
├── src/
│   └── atliq_hrms_assist/
│       └── __init__.py
├── email_sender.py          # SMTP email utility
├── server.py                # MCP server — tools & prompts
├── utils.py                 # Seed data for demo employees
├── pyproject.toml           # Project dependencies
└── .env                     # Environment variables (not committed)

✅ Prerequisites


⚙️ Installation

1. Clone the repository

git clone https://github.com/Ayush-og/atliq-hrms-assist.git
cd atliq-hrms-assist

2. Install dependencies using uv

uv sync

Or install manually:

uv add "mcp[cli]<2.0.0" pydantic python-dotenv

🔐 Configuration

Create a .env file in the project root:

CB_EMAIL=your_gmail_address@gmail.com
CB_EMAIL_PWD=your_gmail_app_password

Note: Use a Gmail App Password, not your regular Gmail password. Enable 2FA on your account first.


🚀 Running the MCP Server

Test that the server runs without errors:

uv run python server.py

🔗 Connecting to Claude Desktop

  1. Open Claude Desktop → Settings → Developer → Edit Config.
  2. Add the following to claude_desktop_config.json:
{
  "mcpServers": {
    "atliq-hr-assist": {
      "command": "C:\\Users\\<your-username>\\.local\\bin\\uv.exe",
      "args": [
        "--directory",
        "C:\\path\\to\\atliq-hrms-assist",
        "run",
        "python",
        "server.py"
      ]
    }
  }
}
  1. Save and restart Claude Desktop.
  2. The atliq-hr-assist connector will appear as 🟢 Connected.

🛠️ Available Tools

👤 Employee Tools

Tool Description Parameters
add_employee Add a new employee emp_name, manager_id, email
get_employee_details Get employee details by name name

🌴 Leave Manager Tools

Tool Description Parameters
get_leave_balance Check remaining leave days employee_id
apply_leave Apply for leave on specific dates employee_id, leave_dates
get_leave_history View past leave records employee_id

📅 Meeting Scheduler Tools

Tool Description Parameters
schedule_meeting Schedule a meeting emp_id, meeting_dt, topic
get_meetings View all scheduled meetings employee_id
cancel_meeting Cancel an existing meeting emp_id, meeting_dt, topic

🎫 Ticket Tools

Tool Description Parameters
create_ticket Raise an equipment/IT request emp_id, item, reason
update_ticket_status Update ticket status ticket_id, status

📧 Email Tool

Tool Description Parameters
send_email Send email to one or more recipients subject, body, to_emails

🤖 Available Prompts

These are pre-built multi-step workflows you can invoke from Claude Desktop via "Add from atliq-hr-assist".

1. onboard_new_employee

Onboards a new employee end-to-end.

Input Description
employee_name Full name of the new employee
manager_name Full name of the reporting manager

Steps performed automatically:

  • Adds employee to HRMS
  • Sends welcome email with login credentials
  • Notifies the manager
  • Raises equipment tickets (laptop, ID card, etc.)

2. apply_leave_request

Processes a leave application for an employee.

Input Description
employee_name Full name of the employee
leave_dates Dates for leave (e.g. "2026-08-22, 2026-08-23")

Steps performed automatically:

  • Looks up employee ID
  • Checks leave balance
  • Applies leave if balance is sufficient
  • Sends confirmation email

3. schedule_meeting_request

Schedules a meeting and sends invites.

Input Description
employee_name Employee's full name
manager_name Manager's full name
meeting_date ISO datetime (e.g. "2026-08-20T10:00:00")
topic Meeting subject

Steps performed automatically:

  • Looks up both employee and manager IDs
  • Schedules the meeting
  • Sends invitation email to both parties

💡 Usage Examples

Ask Claude in natural language:

"Onboard Peter Pandey with Tony Sharma as his manager."
"Apply leave for Tony Sharma on August 22 and 23, 2026."
"Schedule a 1:1 meeting between Peter Pandey and Tony Sharma on August 20 at 10 AM."
"Check leave balance for employee E004."
"Create a ticket for Peter Pandey to get a new laptop."

🧑‍💻 Author

Ayush — @Ayush-og


📄 License

This project is open source and available under the MIT License.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
Exa MCP Server

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。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选