HR-Assist
Automates HR workflows such as employee onboarding, leave management, and ticket tracking through natural language prompts in Claude Desktop.
README
š¤ HR-Assist ā Agentic AI HR Helpdesk
HR-Assist is an Agentic AI system that helps HR teams automate routine workflows using Claude Desktop as the MCP client and a custom Python MCP server as the backend.
This project demonstrates end-to-end automation of the employee onboarding process ā tasks that typically require multiple manual steps are handled by the AI agent in a single prompt.
⨠What It Does
| Task | Automated? |
|---|---|
| Add employee to HRMS | ā |
| Send welcome email with credentials | ā |
| Notify the manager | ā |
| Raise tickets for laptop, ID card & equipment | ā |
| Schedule introductory meeting | ā |
| Leave management | ā |
| Ticket tracking & updates | ā |
šļø Architecture
āāāāāāāāāāāāāāāāāāāāāāā MCP Protocol āāāāāāāāāāāāāāāāāāāāāāā
ā ā āāāāāāāāāāāāāāāāāāāāāāāāāāāŗ ā ā
ā Claude Desktop ā ā HR-Assist Server ā
ā (MCP Client) ā ā (Python + uv) ā
ā ā ā ā
āāāāāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāāāāā
ā
āāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāā
ā¼ ā¼ ā¼
employee_manager leave_manager ticket_manager
meeting_manager schemas utils
- MCP Client ā Claude Desktop
- MCP Server ā This codebase (
server.py+hrms/modules) - Email ā SMTP via Gmail App Password
š Project Structure
HR_helpdesk/
ā
āāā hrms/
ā āāā __init__.py
ā āāā employee_manager.py # Add & fetch employee logic
ā āāā leave_manager.py # Leave apply, balance, history
ā āāā meeting_manager.py # Schedule & fetch meetings
ā āāā ticket_manager.py # Create & update tickets
ā āāā schemas.py # Pydantic data models
ā
āāā server.py # MCP server entry point
āāā utils.py # Shared utility functions
āāā emails.py # Email sending logic (SMTP)
āāā pyproject.toml # Project config (uv)
āāā sample.env # Environment variable template
āāā README.md
āļø Setup Instructions
Prerequisites
- Claude Desktop installed
- uv installed
- Gmail account with App Password enabled
1. Clone the Repository
git clone https://github.com/saibalajijammu/HR_helpdesk.git
cd HR_helpdesk
2. Install Dependencies
uv init
uv add mcp[cli]
3. Set Up Environment Variables
cp sample.env .env
Edit .env and fill in:
CB_EMAIL=your_email@gmail.com
CB_EMAIL_PWD=your_gmail_app_password
4. Configure Claude Desktop
Open your claude_desktop_config.json file and add the following:
Location of config file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"hr-assist": {
"command": "C:\\Users\\<your-username>\\.local\\bin\\uv",
"args": [
"--directory",
"<full-path-to-project>\\HR_helpdesk",
"run",
"server.py"
],
"env": {
"CB_EMAIL": "YOUR_EMAIL",
"CB_EMAIL_PWD": "YOUR_APP_PASSWORD"
}
}
}
}
Replace
<your-username>and<full-path-to-project>with your actual values.
5. Restart Claude Desktop
After saving the config, fully restart Claude Desktop. You should see hr-assist appear as a connected MCP server.
š¬ Usage
Option 1 ā Quick Onboarding via UI
- Click the
+icon in Claude Desktop - Select
Add from hr-assist - Fill in the employee details when prompted
Option 2 ā Custom Prompt (Recommended)
Just type a natural language prompt like:
Onboard a new employee named Priya Mehta under manager Raj Kumar.
The agent will automatically:
- ā Add her to the HRMS
- ā Send a welcome email
- ā Notify her manager
- ā Raise tickets for laptop, ID card & equipment
- ā Schedule an intro meeting
š Environment Variables
| Variable | Description |
|---|---|
CB_EMAIL |
Your Gmail address used for sending emails |
CB_EMAIL_PWD |
Gmail App Password (not your regular password) |
š§° Tech Stack
| Component | Technology |
|---|---|
| AI Model | Claude (Anthropic) |
| MCP Client | Claude Desktop |
| MCP Server | Python + mcp[cli] |
| Package Manager | uv |
| SMTP (Gmail) | |
| Data Validation | Pydantic (schemas.py) |
š¤ Contributing
Pull requests are welcome! For major changes, please open an issue first to discuss what you'd like to change.
š License
This project is licensed under the MIT License.
<p align="center">Built with š§ by <a href="https://github.com/saibalajijammu">Saibalaji Jammu</a></p>
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.