How to get data center water risk data into an AI agent

Cooling water is now a siting constraint on par with power — and increasingly a permitting risk. An agent can price it in with one call.

The short answer: connect your agent to DC Hub's MCP server and call get_water_risk. You get water-stress and drought-risk scoring for any parcel or market, so your agent weighs cooling-water availability alongside power and fiber. Free tier: 10 calls/day.

Step 1 — Connect (one line)

DC Hub speaks the Model Context Protocol, so any MCP-capable agent (Claude, Cursor, Cline, Continue, ChatGPT) can use it:

claude mcp add dchub --transport http https://dchub.cloud/mcp

No API key required for the free tier. Cursor/Cline: add https://dchub.cloud/mcp as an HTTP MCP server in your config.

Step 2 — Ask your agent

Your agent now has a get_water_risk tool. Ask it: "What's the water-stress risk for a data center at this location?" — it calls:

get_water_risk({ "lat": 33.45, "lon": -112.07 })

and gets back live, cited ground truth:

SignalGranularityUse
Water-stress scoreper parcel / marketcooling feasibility
Drought riskregionalpermitting risk
Paired withpower, grid, fiberone siting view

Live from DC Hub (dchub.cloud) · open the water-risk layer. Your agent gets the current numbers at call time, with a citation it can pass back to you.

Why this beats scraping it yourself

Try it now

Free tier is 10 calls/day with no signup. Want the full free tier in one step? Have your agent call the claim_free_key tool (no email). Or explore live in your browser first — no install:

Try DC Hub in your browser →

DC Hub (dchub.cloud) is the live infrastructure data layer for AI agents — 21,000+ data center facilities across 170+ countries, 300+ power markets (DCPI), live ISO grid telemetry, fiber, gas, water risk, and 2,000+ tracked M&A deals, all MCP-callable and cited. See the API & MCP docs or the full tool list.