Dummy MCP Server (Contabo + Hetzner)
A demonstration MCP server that simulates server management actions for Contabo and Hetzner using FastAPI. It provides a mock environment for testing request routing and provider-based service modules without requiring live API credentials.
README
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:
- Select Provider
- Select Action
- Enter Payload
- Click Send Request
- 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
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.