Steddion Energy MCP Server
Provides tools for Dutch energy market data: day-ahead and imbalance prices, weather forecasts, and battery storage business case calculations.
README
Steddion Energy MCP Server
MCP-server voor de Nederlandse energiemarkt: day-ahead prijzen, onbalansprijzen, weersvoorspellingen en BESS-businesscases.
Tools
| Tool | Beschrijving |
|---|---|
get_day_ahead_prices |
Uurlijkse day-ahead prijzen (EUR/MWh) via ENTSO-E |
get_imbalance_prices |
Kwartierlijkse onbalansprijzen via TenneT |
get_weather_forecast |
Wind, zon (GHI) en temperatuur via Open-Meteo |
calculate_bess_business_case |
Day-ahead arbitrage-opbrengst voor een batterij |
Installatie & draaien
Vereisten
- Python 3.11+
- uv (package manager)
Installeren
git clone https://github.com/lars-kerkhof/mcp-steddion.git
cd mcp-steddion
uv sync
Environment variabelen
cp .env.example .env
# Bewerk .env en vul je ENTSO-E API token in (optioneel — zonder token draait de server op mock-data)
| Variabele | Vereist | Beschrijving |
|---|---|---|
ENTSOE_API_TOKEN |
Nee | Token van ENTSO-E Transparency Platform. Zonder token worden realistische mock-data gebruikt. |
HOST |
Nee | Server host (default: 0.0.0.0) |
PORT |
Nee | Server port (default: 8000) |
Server starten
uv run python -m steddion_mcp
De server draait dan op http://localhost:8000/mcp.
Tests draaien
uv run pytest
Koppelen aan ChatGPT (Developer Mode)
ChatGPT ondersteunt geen lokale stdio-servers. Je moet de server via HTTPS bereikbaar maken.
Stap 1: Server starten
uv run python -m steddion_mcp
Stap 2: Tunnel opzetten
Kies een van:
Cloudflared (aanbevolen):
cloudflared tunnel --url http://localhost:8000
ngrok:
ngrok http 8000
Je krijgt een HTTPS-URL, bijvoorbeeld https://abc123.trycloudflare.com.
Stap 3: Connector toevoegen in ChatGPT
- Open ChatGPT → Settings → Apps/Connectors
- Schakel Developer Mode in
- Klik Add Connector → Custom
- Vul de URL in:
https://<jouw-tunnel-url>/mcp - Sla op — de tools verschijnen nu in ChatGPT
Architectuur
steddion_mcp/
├── server.py # FastMCP server, tool-registraties
├── entsoe.py # ENTSO-E day-ahead prijzen
├── tennet.py # TenneT onbalansprijzen
├── weather.py # Open-Meteo weersdata
├── bess.py # BESS businesscase calculator
├── models.py # Pydantic response-modellen
├── mock_data.py # Realistische mock-data generators
└── __main__.py # Entry point
Mock-data
Alle tools vallen automatisch terug op deterministische mock-data wanneer:
- De
ENTSOE_API_TOKENontbreekt (day-ahead prijzen) - De TenneT API niet bereikbaar is (onbalansprijzen)
- De Open-Meteo API niet bereikbaar is (weer)
Mock-data is herkenbaar aan het veld source: "mock" in de response.
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.