Installation überspringen. In unter 2 Minuten einsatzbereit.
Starte eine kostenlose Testphase auf cloud.anythingmcp.com, füge DC Hub mit einem Klick hinzu und richte deinen KI-Client (Claude, ChatGPT, Copilot oder Cursor) auf den erzeugten MCP-Endpoint. Kein Docker, kein git clone, keinerlei Entwicklungserfahrung nötig.
Summary
Data centre and power-grid intelligence from DC Hub: facilities worldwide, market power-readiness scores, the US interconnection queue, construction pipeline, M&A transactions, live ISO grid fuel mix and electricity prices, plus site scoring and multi-site ranking. Twelve of the sixteen tools work without an API key.
Frag einfach
Beispiel-Prompts für DC Hub
Klick auf einen Prompt, um ihn zu kopieren. In Claude, ChatGPT, Cursor, Gemini, Copilot oder OpenClaw einfügen — und gegen diesen Connector laufen lassen.
Claude ist KI und kann Fehler machen. Bitte Antworten gegenprüfen.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → DC Hub klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
DC Hub + Gemini
Data centre and power-grid intelligence from DC Hub: facilities worldwide, market power-readiness scores, the US interconnection queue, construction pipeline, M&A transactions, live ISO grid fuel mix and electricity prices, plus site scoring and multi-site ranking. Twelve of the sixteen tools work without an API key.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
(none — public API)
Schritt 1 — Zugangsdaten holen
Data centre and energy-grid intelligence for site selection, infrastructure investment and power analysis.
What works without a key, and what does not
Twelve of the sixteen tools answer anonymously, so the connector installs in one click and most questions work immediately. Four do not, and they fail in two different ways.
403 without a key — dchub_pipeline, dchub_grid_fuel_mix, dchub_energy_prices. A free developer key unlocks these.
403 even with a free key — dchub_site_score requires DC Hub's paid Pro plan. No free key unlocks it. Treat it as unavailable unless the workspace holds a Pro key.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —DC Hubsollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| Tool | What it does |
|---|---|
dchub_stats | Platform-wide statistics: total facilities tracked, countries, providers and aggregate capacity in MW |
dchub_search_facilities | Search DC Hub's data centre facilities by free text (city, provider or market name) and/or country |
dchub_facility_detail | Full record for one facility: contacts, capacity detail and certifications |
dchub_list_markets | List every tracked data centre market with summary statistics |
dchub_compare_markets | Side-by-side comparison of two or more data centre markets |
dchub_market_dcpi | DC Hub Power Index for one market: a BUILD / CAUTION / AVOID verdict plus composite_score, excess_power_score, constraint_score and time_to_ |
dchub_ai_capacity_index | Markets ranked by AI-ready deployable MW for near-term large-load siting, with a hyperscale_ready flag and an ai_ready_mw proxy |
dchub_interconnection_queue | Filter the ~5,300-project US interconnection queue (7 ISOs) server-side, so you receive the survivors instead of the raw ~1,744 GW queue |
dchub_pipeline | Data centres under construction or announced — the forward supply picture for a market |
dchub_transactions | Recent data centre M&A: acquisitions, investments, joint ventures, leases and development deals |
dchub_news | Latest data centre industry news, aggregated from 40+ sources |
dchub_site_score | Suitability score (0-100) for data centre development at one specific location |
dchub_grid_fuel_mix | Real-time fuel mix of a US power grid, refreshed about every 60 seconds |
dchub_energy_prices | Electricity pricing for one US state — the input to any operating-cost estimate for a site in that state |
dchub_analyze_parcel | Structured read of a GeoJSON parcel boundary: geodesic acreage, the largest member's centroid as a representative point (never the centre of |
dchub_rank_sites | Deterministic ranking of candidate sites under hard constraints and signed weighted objectives |
FAQ
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?
