🚀 IT HelpDesk MCP Server

A production-ready Model Context Protocol (MCP) server built using FastMCP that enables Claude Desktop to intelligently classify IT support tickets, estimate ticket priority, generate troubleshooting steps, and predict expected resolution times.

📌 Overview

This project demonstrates how to build and integrate a custom MCP server with Claude Desktop using FastMCP.

Instead of hardcoding business logic inside an AI assistant, this MCP server exposes reusable tools that Claude can invoke whenever users ask IT support-related questions.

This project serves as a beginner-friendly introduction to the Model Context Protocol (MCP) ecosystem.

Related MCP server: Customer Support MCP Server

✨ Features

✅ Ticket Classification

• Network Issues

• Hardware Issues

• Email Issues

• Access Management

• General Support

✅ Priority Estimation

Automatically estimates ticket priority based on business rules.

✅ Troubleshooting Generator

Provides standard troubleshooting steps for:

• VPN

• Password Issues

• Email Problems

• General Issues

✅ Resolution Time Estimation

Predicts expected resolution time based on ticket priority.

🛠 Tech Stack

• Python 3.12+

• FastMCP

• Claude Desktop

• Model Context Protocol (MCP)

• uv Package Manager

📂 Project Structure

IT-HelpDesk-MCP/
│
├── main.py
├── pyproject.toml
├── uv.lock
├── README.md
├── .gitignore
│
├── screenshots/
│   ├── claude-desktop.png
│   ├── terminal.png
│   └── tool-call.png
│
└── examples/
    └── sample-prompts.md

⚙️ Installation

Clone Repository

git clone https://github.com/shrishail07/IT-HelpDesk-MCP.git

cd IT-HelpDesk-MCP

Install Dependencies

Using uv

uv sync

or

uv pip install -r requirements.txt

Start MCP Server

uv run python main.py

Expected Output

Starting IT HelpDesk MCP Server...
Listening on http://0.0.0.0:8080

🔌 Claude Desktop Integration

Install the MCP server into Claude Desktop.

uv run fastmcp install claude-desktop main.py

Restart Claude Desktop after installation.

🧰 Available MCP Tools

1️⃣ classify_ticket()

Classifies an IT support ticket.

Example

Input

My VPN is not connecting.

Output

{
  "category": "Network",
  "assigned_team": "Infrastructure Team"
}

2️⃣ estimate_priority()

Example

Input

Production application is down.

Output

{
  "priority": "Critical",
  "expected_sla": "1 Hour"
}

3️⃣ generate_troubleshooting_steps()

Example

Input

VPN

Output

[
  "Check internet connectivity.",
  "Restart the VPN client.",
  "Verify your credentials.",
  "Reconnect to the VPN."
]

4️⃣ estimate_resolution_time()

Input

High

Output

Within 8 Hours

💬 Example Prompts

Inside Claude Desktop

Use the IT HelpDesk MCP Server to classify this ticket.

My VPN is not connecting.

Estimate priority for

Production application is down.

Generate troubleshooting steps for VPN.

Estimate resolution time for High priority.

🏗 Architecture

                     +----------------------+
                     |   Claude Desktop     |
                     +----------+-----------+
                                |
                     Model Context Protocol
                                |
                                ▼
                  +----------------------------+
                  |   IT HelpDesk MCP Server   |
                  |        (FastMCP)           |
                  +-------------+--------------+
                                |
        +-----------+-----------+-----------+-----------+
        |           |                       |           |
        ▼           ▼                       ▼           ▼
 classify_ticket() estimate_priority() troubleshooting() resolution()

📷 Demo

Claude Desktop

Add screenshot here

screenshots/claude-desktop.png

MCP Server Running

Add screenshot here

screenshots/terminal.png

Tool Invocation

Add screenshot here

screenshots/tool-call.png

🚀 Future Improvements

• AI-based ticket summarization

• ServiceNow Integration

• Jira Integration

• Email Automation

• Database Logging

• Oracle Integration

• LangGraph Agent Support

• RAG-powered Knowledge Base

• Authentication

• Docker Deployment

• Kubernetes Deployment

🎯 Learning Outcomes

This project demonstrates:

• Model Context Protocol (MCP)

• FastMCP Server Development

• Claude Desktop Integration

• Tool Calling

• Business Rule Automation

• Python Backend Development

🤝 Contributing

Contributions are welcome.

1. Fork the repository

2. Create a feature branch

3. Commit your changes

4. Open a Pull Request

📄 License

This project is licensed under the MIT License.

👨‍💻 Author

Shreeshail Mali

Oracle PL/SQL Developer | Python Developer | AI Engineer

• GitHub: https://github.com/shreeshail07

• LinkedIn: https://linkedin.com/in/shreeshail-mali-sm007/

⭐ If you found this project useful, please consider giving it a Star.