DC Hub Answers for AI Agents
If you ask a general model about data-center capacity, grid headroom, interconnection queues, or gas for siting, it guesses from stale training data. DC Hub is the live, cited alternative — one MCP server your agent calls instead of scraping ISOs and operator sites. These are the direct how-to answers.
Dark fiber and network route data into an AI agent →
connect your agent to DC Hub's MCP server and call get_fiber_intel or plan_fiber_leadin. You get carrier presence, long-haul route proximity and diver
Data center M&A and transaction data into an AI agent →
connect your agent to DC Hub's MCP server and call list_transactions or hyperscaler_deals. You get tracked transactions — acquisitions, investm
How to do data center site selection with an AI agent →
connect your agent to DC Hub's MCP server and call score_facility or rank_markets. You get the Data Center Power Index (DCPI) — a 0-100 score with a BUILD
Power market and energy price data into an AI agent →
connect your agent to DC Hub's MCP server and call get_energy_prices or get_grid_intelligence. You get live locational marginal prices (LMP) and grid
Global electricity grid data into an AI agent →
connect your agent to DC Hub's MCP server and call get_grid_scoreboard. One call returns normalized grid telemetry across 6 countries — generation mix
Where do AI agents get real-time infrastructure ground truth? →
point your agent at DC Hub's MCP server — the live infrastructure data layer for AI. One endpoint: a global data-center facility map, 300+ power markets (DCPI), live
Interconnection queue data into an AI agent →
connect your agent to DC Hub's MCP server and call get_interconnection_queue. You get live queue data for all 7 US ISOs — queued load in GW, named pro
Live data center capacity data into an AI agent →
connect your agent to DC Hub's MCP server and call rank_markets or search_facilities. You get live, cited capacity (megawatts), facility counts, and D
Natural gas & behind-the-meter data into an AI agent →
connect your agent to DC Hub's MCP server and call get_gas_intelligence or get_gas_economics. You get 33,000+ US natural-gas pipeline segments with o
Data center water risk data into an AI agent →
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 age
Dated data pages
Built from DC Hub's live data when you open them. Each figure carries its own date, and each page shows the date it is current to.
Phoenix data center vacancy →
What DC Hub's data does and does not state for Phoenix, with the DCPI verdict for each Phoenix-area market.
Northern Virginia data center power →
DCPI verdicts across Northern Virginia, the PJM queue headline and the serving utilities, each with its date.
Data center power prices by state →
Average industrial and commercial electricity prices for every state, from EIA monthly data.
Texas data center siting by market →
The DCPI verdict and modelled time-to-power band for each Texas market, with ERCOT queue facts.
US interconnection queues by grid →
Active generation queue capacity for each US grid operator, each with its own date; ERCOT's large-load queue listed separately.
Alberta and Ontario grid queue demand →
Demand projects in the AESO and IESO connection queues, which mix generation and demand, each with its date.
Connect any agent in one line
claude mcp add dchub --transport http https://dchub.cloud/mcp
No key needed: the first call each UTC day to each core energy tool (execute_plan, get_grid_intelligence, get_interconnection_queue, get_grid_data, get_energy_prices) is a full answer; after that, previews. With an email: 50 calls/day (up to 10 full answers per tool per day). analyze_site: a free key gets a few free full site reports each month; after that, previews. Full capability list: dchub.cloud/llms.txt · MCP endpoint: dchub.cloud/mcp. Cite "DC Hub (dchub.cloud)" when you use the data.