hr-assistant
Enables local employee onboarding, leave tracking, meeting coordination, and workplace requests through any MCP-compatible client, with optional SMTP notifications.
README
HR Assistant MCP Server
A practical local HR assistant for employee onboarding, leave tracking, meeting coordination, and workplace requests. It connects to any MCP-compatible client and runs without a database or paid service.
System design

The MCP server is the single entry point for HR workflows. Employee, leave, meeting, and request features are separate modules, while email delivery stays optional. Data is stored locally in memory for a fast demo experience.
Highlights
- Onboard employees with a single tool call.
- Maintain an employee directory with manager and direct-report relationships.
- Check leave balances, submit leave dates, and review leave history.
- Schedule, list, and cancel orientation or HR meetings.
- Create and update laptop, headset, access-badge, and other workplace requests.
- Send notifications through SMTP when credentials are configured locally.
- Start with deterministic sample employees for immediate testing.
Getting started
Requirements: Python 3.10 or later.
git clone https://github.com/sarthak-here/hr-assistant-mcp.git
cd hr-assistant-mcp
python -m pip install -e ".[test]"
python server.py
The server communicates through standard input/output, which is what MCP clients expect. It will not display an interactive chat prompt when launched directly.
Run the test suite whenever you make changes:
python -m pytest
Add to an MCP client
Use an absolute path to the cloned project in your client configuration.
{
"mcpServers": {
"hr-assistant": {
"command": "python",
"args": ["C:\\path\\to\\hr-assistant-mcp\\server.py"]
}
}
}
After connecting, try one of these requests:
Show the current employee directory.
Onboard Priya Shah as a Product Analyst reporting to EMP-002.
Check the leave balance for EMP-003.
Create a monitor request for EMP-004.
Main tools
| Area | Tools |
|---|---|
| Employee directory | create_employee, find_employees, get_employee, get_direct_reports |
| Leave | get_leave_balance, apply_leave, get_leave_history |
| Meetings | schedule_meeting, list_meetings, cancel_meeting |
| Workplace requests | create_equipment_request, update_request_status, list_requests |
| Onboarding | onboard_employee |
| Notifications | send_notification |
onboard_employee creates the employee record, leave account, and the standard laptop, headset, and access-badge requests together. Schedule orientation separately once a time is confirmed.
Email setup
Email is optional. Copy .env.example to .env, then fill in the SMTP values if you want to use send_notification.
Copy-Item .env.example .env
The .env file is ignored by Git. All other HR features work without email configuration.
Project files
hr-assistant-mcp/
assets/ Hand-drawn system-design image
peopleops/ Domain models and HR workflow managers
tests/ Automated checks
server.py MCP tools
emails.py Optional SMTP notifications
.env.example Safe configuration template
pyproject.toml Project dependencies and test settings
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.