The DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, Fiber MCP server,
connected in one click.

“Use “search”: Search DC Hub for relevant records (OpenAI Deep Research / ChatGPT connector format). Returns a list of matching data-center facilities as {.”

“Use “fetch”: Fetch a DC Hub record for an id returned by the `search` tool (OpenAI Deep Research / ChatGPT connector format). Returns {id, title, text, u.”

“Use “execute_plan”: Unified data-center siting, power-grid capacity and AI-compute infrastructure planner — megawatts and power density, grid headroom and power.”

“Use “search_facilities”: FRONT DOOR CHECK — if the ask is "find <N> MW in <market>" or otherwise wants power / fiber / water / verdict context ATTACHED to the hits,.”

search — Search DC Hub for relevant records (OpenAI Deep Research / ChatGPT connector format). Returns a list of matching data-center facilities as {

fetch — Fetch a DC Hub record for an id returned by the `search` tool (OpenAI Deep Research / ChatGPT connector format). Returns {id, title, text, u

execute_plan — Unified data-center siting, power-grid capacity and AI-compute infrastructure planner — megawatts and power density, grid headroom and power

search_facilities — FRONT DOOR CHECK — if the ask is "find <N> MW in <market>" or otherwise wants power / fiber / water / verdict context ATTACHED to the hits,

get_facility — Full metadata for one facility — name, operator, address, lat/lon, power capacity (MW total/used), cooling type, fiber providers (count + ca

get_market_intel — Use when a user asks about ONE data-center market — vacancy, capacity pricing, supply pipeline, dominant operators, YoY growth — across any

get_market_dcpi_rank — DCPI rank for a single market: BUILD/CAUTION/AVOID verdict, 0-100 composite_score (verdict-aware), excess_power_score, constraint_score, tim

predict_market_trajectory — Forecast a DCPI market's near-term trajectory (next 1-8 quarters). Projects excess_power_score and constraint_score forward with confidence