Skip to main content
Glama
MRUK31

Dummy MCP Server (Contabo + Hetzner)

by MRUK31
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Dummy MCP Server (Contabo + Hetzner)

This project is a dummy MCP server built for interview/demo purposes.
It simulates the behavior of an MCP (Model Control Plane) server that connects to service providers like Contabo and Hetzner, but without calling real APIs.

Why dummy Service providers?

Since, in order to utilize Contabo and Hetzner services, we have to go through payment and billing. Therefore, to understand the basic working of MCP with service providers, we created fake instances!

Purpose

The goal of this project is to demonstrate:

  • Clean architecture

  • Request routing logic

  • Provider-based service modules

  • Working client-server flow

  • Frontend dialog response display

  • Interview-ready demo

Features

✔ Dummy MCP server with clean request routing
✔ Two service providers (Contabo & Hetzner)
✔ Dummy “create_server” & “delete_server” actions
✔ Frontend UI with dialog box to show response
✔ CORS enabled for browser requests
✔ Easy to extend (add real APIs later)

Architectural Diagram

┌─────────────────────┐ │ MCP Client │ │ (Frontend / CLI) │ └─────────┬───────────┘ │ POST /mcp │ ┌──────────▼───────────┐ │ MCP Server │ │ (FastAPI) │ └──────────┬───────────┘ │ ┌───────────────┴───────────────┐ │ │ ┌───────▼────────┐ ┌────────▼───────┐ │ ContaboService │ │ HetznerService │ │ (Dummy Logic) │ │ (Dummy Logic) │ └────────────────┘ └────────────────┘

Step-by-Step Setup (Commands Used)

1. Create project folder

mkdir mcp-server cd mcp-server

2. Initialize Git

git init

3. Create Python Virtual Environment

python3 -m venv venv source venv/bin/activate

4. Install dependencies

pip install fastapi uvicorn

5. Save dependencies

pip freeze > requirements.txt

6. Create folders & files

mkdir services touch main.py touch services/contabo.py touch services/hetzner.py touch index.html touch README.md

Running the Server

uvicorn main:app --reload --port 3000

You should see:

INFO: Uvicorn running on http://127.0.0.1:3000

Testing via Curl (Contabo)

curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -d '{ "provider": "contabo", "action": "create_server", "payload": {"name": "test-server", "ram": "4GB"} }'

Testing via Curl (Hetzner)

curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -d '{ "provider": "hetzner", "action": "create_server", "payload": {"name": "hetzner-server", "ram": "8GB"} }'

Frontend Demo

Open index.html in your browser and:

  1. Select Provider

  2. Select Action

  3. Enter Payload

  4. Click Send Request

  5. Response appears in a dialog box

Logic Explanation

1. MCP Server (main.py)

  • Receives POST request at /mcp

  • Checks provider name

  • Routes request to respective service module

2. Contabo Service (services/contabo.py)

  • Simulates server creation & deletion

  • Returns fake server ID

3. Hetzner Service (services/hetzner.py)

  • Same dummy logic as Contabo

GitHub Push Commands

git add . git commit -m "Initial dummy MCP server implementation" git branch -M main git remote add origin https://github.com/<your-username>/mcp-server.git git push -u origin main

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

How are these scores calculated?

Resources

New MCP Servers

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/MRUK31/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server