PVGIS MCP

PVGIS MCP

MCP server that estimates photovoltaic production using the European Commission's PVGIS API, deployed on Cloudflare Workers for serverless, free-tier operation.

Category
Visit Server

README

PVGIS MCP — Cloudflare Worker

Remote MCP server che stima la produzione fotovoltaica di un impianto via PVGIS (Photovoltaic Geographical Information System, Commissione Europea / JRC). Gira dentro Cloudflare (serverless, sempre acceso, niente Mac acceso).

Questo connettore è usato dal plugin valutazione-fv del marketplace AI, MAX Plugins — materiale didattico dei workshop AI, MAX. La skill recupera da qui la produzione reale di un tetto e la passa al suo script di calcolo ROI.

API PVGIS: pubblica, gratuita, senza key. Worker su Cloudflare: free tier (100.000 richieste/giorno incluse) — costo atteso €0.

Endpoint MCP una volta deployato: https://<worker>.workers.dev/mcp

Tool esposti

  • pv_production (lat, lon, peakpower_kwp, angle=30, aspect=0, loss=14) → produzione annua + mensile, irraggiamento.
  • monthly_radiation (lat, lon, angle=30, aspect=0) → irraggiamento mensile.

aspect: 0 = SUD, -90 = est, 90 = ovest. angle: inclinazione falda in gradi.


Deploy — via GitHub (consigliato)

  1. Questo è il contenuto del repo github.com/maxturazzini/pvgis-mcp.
  2. Su Cloudflare: Workers & Pages → Create → Workers → Connect GitHub → seleziona pvgis-mcp.
  3. Cloudflare rileva wrangler.jsonc, installa le dipendenze e fa il build/deploy.
  4. Ad ogni git push su maindeploy automatico.
  5. URL finale: https://pvgis-mcp.<tuo-subdominio>.workers.dev

Deploy — via CLI (alternativa)

cd worker-cloudflare
npm install
npx wrangler login        # apre il browser, autorizza
npx wrangler deploy       # stampa l'URL del worker

Collegare a Claude.ai

Claude.ai → Impostazioni → ConnettoriAggiungi connettore personalizzato (BETA):

  • Nome: PVGIS
  • URL del server MCP remoto: https://pvgis-mcp.<tuo-subdominio>.workers.dev/mcp
  • OAuth: lasciare vuoto (il server è pubblico, no-auth).
  • Aggiungi.

Poi in chat attiva il connettore PVGIS e chiedi la produzione di un tetto date le coordinate.

Test rapido dopo il deploy

# health check
curl https://pvgis-mcp.<tuo-subdominio>.workers.dev/
# handshake MCP (atteso: 200 + serverInfo "pvgis")
curl -sL -X POST https://pvgis-mcp.<tuo-subdominio>.workers.dev/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"probe","version":"1"}}}'

Note

  • No-auth: chiunque conosca l'URL può usarlo. Per un tool read-only su dati pubblici (PVGIS) è accettabile; se vuoi limitarlo, si aggiunge OAuth (Workers OAuth Provider) — non incluso qui per semplicità.
  • Geocoding: PVGIS prende coordinate, non indirizzi. Per accettare un indirizzo serve un geocoder a monte (es. Nominatim/OSM, libero). Non incluso: lo si può aggiungere come terzo tool.
  • La versione Python stdio (../server.py) resta per Claude Desktop; la versione tunnel (../server_http.py + ../run_tunnel.sh) resta come alternativa locale.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured