suresh-hr-assist
Automates HR workflows such as employee onboarding, leave management, meeting scheduling, and ticket handling through natural language, with email notifications and demo data.
README
Suresh Amgoth HR Assist
Suresh Amgoth HR Assist is a Python-based agentic HR workflow project built around the Model Context Protocol. It automates common HR tasks such as employee onboarding, email notifications, leave management, meeting coordination, and ticket handling through a Claude Desktop compatible MCP server.
The project is structured as a lightweight local service that can be run on a Windows machine and connected to Claude Desktop for interactive HR operations. The code is organized into small service classes, typed request schemas, and reusable tools so the workflow stays easy to extend.
Core Features
- Employee onboarding and lookup
- Leave balance, leave application, and leave history tracking
- Meeting scheduling and cancellation
- IT and HR ticket creation with status updates
- Email notifications for onboarding and support workflows
- Seeded demo data for quick local testing
Tech Stack
- Python 3.10+
- Model Context Protocol (MCP)
- Claude Desktop
- Pydantic
- SMTP email integration
Local Setup
- Open the project folder on your computer.
- Create a virtual environment and install the dependencies.
- Set your email credentials in the environment file.
- Point Claude Desktop to this project folder and run the MCP server.
Claude Desktop Configuration
Use a local path that matches your machine. If this repository is stored under your Windows user profile, a configuration like the following works well:
{
"mcpServers": {
"suresh-hr-assist": {
"command": "uv",
"args": [
"--directory",
"%USERPROFILE%\\OneDrive\\Desktop\\Project\\GenAI_Project3_Resources\\GenAI_Project3_Resources",
"run",
"server.py"
],
"env": {
"CB_EMAIL": "your-email@example.com",
"CB_EMAIL_PWD": "your-app-password"
}
}
}
}
Email Setup
- Set
CB_EMAILto the account that will send notification emails. - Set
CB_EMAIL_PWDto the app password generated by your email provider. - Update the sender address in the project code if you want to use a different domain.
Screenshot
<img src="Resources/image.jpg" alt="Claude Desktop prompt showing the HR Assist workflow" style="width:auto;height:300px;padding-left:30px">
Personal Project Summary
This project is presented as part of Suresh Amgoth's portfolio to demonstrate practical AI workflow automation, structured Python design, and MCP-based tool integration.
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.