HR System MCP Server
Supports running the server locally with Docker for development and testing.
Provides Okta OAuth 2.0 token validation for all tool calls, ensuring secure access to HR system functionality such as employee information lookup, directory listing, payroll access, and time-off request management.
Supports deployment on Railway.com as a long-running server for constant traffic and unlimited request duration.
Supports deployment on Vercel as a serverless function for sporadic usage and automatic scaling.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@HR System MCP Serverget employee with ID 42"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HR System MCP Server
An unofficial prototype MCP server providing HR system functionality with Okta token validation. For evaluation and testing purposes only.
📚 Documentation
Complete documentation available in the docs/ folder:
docs/RAILWAY_README.md - Deploy to Railway.com (3 steps) 🚀
docs/DOCKER_QUICK_START.md - Run locally with Docker 🐳
docs/README_INTEGRATION.md - Use the deployed server 🔌
docs/CLAUDE.md - Developer guide & architecture 💻
docs/INDEX.md - Complete documentation index 📖
Overview
The HR System MCP Server provides:
✅ Employee information lookup
✅ Employee directory listing
✅ Payroll information access
✅ Time-off request management
✅ Okta OAuth 2.0 token validation for all tool calls
✅ HTTP/NDJSON streaming support (FastMCP)
✅ Ready for Railway deployment 🚀
Authentication
This server validates Okta access tokens for all tool calls (except initialize):
Token Source: Okta authorization server
Validation: JWT signature, expiration, audience claims
Authorization Header:
Authorization: Bearer <access_token>
Quick Start
# Setup
cp env.example .env
# Edit .env with your Okta credentials
# Install dependencies
pip install -r requirements.txt
# Run in HTTP mode (for Okta MCP Adapter)
python main.py --http 8001Configuration
.env (Environment Variables)
OKTA_DOMAIN=ijtestcustom.oktapreview.com
OKTA_AUTHORIZATION_SERVER_ID=auss2fth0mcIXHzVO1d7
OKTA_AUDIENCE=
OKTA_REQUIRED_SCOPES=
# When true (default), tools/list without auth returns 401. When false, allows unauthenticated tools/list (e.g. for gateway registration).
# PROTECTED_DISCOVERY=trueAvailable Tools
Tool | Description | Parameters |
| Get employee by ID |
|
| List all employees | None |
| Get payroll info |
|
| Get time-off requests |
|
Usage Examples
Direct via VS Code/Copilot
# Endpoint
http://localhost:8001/mcp
# Authorization
Authorization: Bearer <okta_access_token>Via Okta MCP Adapter Gateway
# Gateway will:
# 1. Receive request from client
# 2. Validate Okta token
# 3. Forward to HR System MCP
# 4. Attach authorization headerImplementation Details
Framework: FastMCP 3.0.0b1
Server: Uvicorn (async HTTP)
Protocol: MCP (Model Context Protocol) with NDJSON streaming
Token Validation: JWKS-based JWT validation with signature verification
Caching: JWKS keys cached with TTL
Request Flow
Client Request
↓
Authorization Header (Okta token)
↓
Initialize (no token needed)
↓
tools/list (validate token)
↓
tools/call (validate token)
↓
Response🚀 Deployment Options
Vercel (Serverless) ⚡
Deploy as serverless function - automatic scaling, pay-per-use
✅ Best for: Sporadic usage, automatic scale-to-zero
✅ Free tier: 100GB bandwidth/month
⚠️ Constraint: 10-second timeout (free), 5-min (Pro)
📖 Guide: docs/VERCEL_README.md
Railway.com (Traditional Server) 🚂
Deploy as long-running server - always-on, unlimited timeout
✅ Best for: Constant traffic, persistent connections
✅ Free tier: 500 hours/month ($5/month after)
✅ No timeout: Unlimited request duration
📖 Guide: docs/RAILWAY_README.md
Docker (Local Development) 🐳
Run locally with Docker - full control, testing
📖 Guide: docs/DOCKER_QUICK_START.md
docker-compose up -dRecommendation:
Use Vercel for sporadic/unpredictable usage (cheaper, auto-scales)
Use Railway for constant traffic or if you need long timeouts
Troubleshooting
See docs/RAILWAY_DEPLOYMENT.md for complete troubleshooting guide.
Quick fixes:
Token validation fails: Verify
OKTA_DOMAINandOKTA_AUTHORIZATION_SERVER_IDin.envPort already in use: Change port in startup command:
python main.py --http 8002Missing environment variables: Copy
.envexample and fill in valuesJWKS fetch error: Verify Okta domain and authorization server ID are correct
Project Structure
hr-mcp-server/
├── main.py # FastMCP server with HTTP handler
├── requirements.txt # Python dependencies
├── Dockerfile # Docker container definition
├── docker-compose.yml # Docker Compose configuration
├── railway.json # Railway deployment config
├── deploy-railway.sh # Deployment helper script
├── test_server.sh # Server test script
├── auth/ # Authentication module
│ ├── __init__.py
│ └── okta_validator.py # Okta token validation
└── docs/ # Documentation
├── INDEX.md # Documentation index
├── RAILWAY_README.md # Railway quick start
├── RAILWAY_DEPLOYMENT.md # Complete deployment guide
├── DOCKER_QUICK_START.md # Docker reference
├── README_INTEGRATION.md # Usage guide
├── CLAUDE_CODE_SETUP.md # Claude Code setup
├── CLAUDE.md # Developer documentation
└── ...more docsSee docs/INDEX.md for complete documentation guide.
Testing
# Using curl with Okta token
curl -X POST http://localhost:8001/mcp \
-H "Authorization: Bearer <your_okta_token>" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list",
"params": {}
}'📖 Documentation
For complete documentation, see the docs/ folder:
Getting Started - Documentation index
Deploy to Railway - Cloud deployment guide
Run with Docker - Local development
Integration Guide - How to use the server
Developer Guide - Architecture & development
References
Status
⚠️ Unofficial Prototype - For evaluation and testing only. Not for production use.
License: Apache 2.0
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BalaGanaparthi/hr-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server