DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, Fiber

Use when a user asks "what is being built / announced / permitted" in a market or by an operator — the forward-looking construction pipeline. Example: "What data centers are under construction in Northern Virginia and when do they come online?" — get_pipeline country=US status=construction (there is no `market` parameter — filter by country/operator, or use search_facilities for a named market). Params: status one of "announced" | "permitted" | "construction" | "operational"; operator (e.g. "Equinix", "Digital Realty", "AWS"); country (ISO-2, e.g. "US", "DE"); min_capacity_mw (e.g. 50 to filter hyperscale); expected_completion_before (ISO date, e.g. "2027-01-01"); limit/offset for pagination. Returns: {projects:[{name, operator, capacity_mw, status, expected_commissioning, market_slug, country, lat, lon}], total, generated_at}. Do NOT use for already-operational facilities (use search_facilities) or for the M&A deal flow (use list_transactions). limit 1-500 (free 25), offset 0-100000. Empty data = no project matches: relax status/operator/min_capacity_mw.

Use this whenever the user asks when power will be available, or about time-to-power, in a US state. Power-availability TIMING for one US state — when power gets EASIER, year by year. Composes: new generation coming online from EIA-860M monthly, split by confidence class (under-construction vs planned vs testing — never blended); scheduled retirements as dated subtractions; LBNL interconnection-queue depth as congestion context (NO delivery dates — the feed has none and most queued MW never completes). The one derived number, cumulative_firm_signal_mw, counts ONLY under-construction+testing minus retirements — speculative permitting-stage MW is shown but never folded in. Answers "when is new capacity landing in Ohio", "what comes online in Georgia by 2027" with dated, sourced, per-lane-vintaged numbers. HONESTY LINE: supply-side signals, not a load-interconnection promise — generation ≠ deliverable load, and utility study timelines / large-load tariff processes / substation-grain delivery are declared out of coverage in constraint_coverage rather than estimated. Try: get_power_availability_timeline state=OH.

Use when a user asks WHERE NEW POWER GENERATION is coming online (the forward supply pipeline) — e.g. "how much new generation is planned in Virginia / the Southeast / ERCOT, and when?". Planned, permitting, and under-construction generators NATIONWIDE from EIA-860M, INCLUDING non-ISO regions (TVA, Southern Co, Arizona PS, PacifiCorp, LADWP) that interconnection-queue feeds miss. Each generator has location (lat/lng), state, county, balancing authority, technology/fuel (solar photovoltaic, onshore wind, natural-gas combined cycle, batteries, nuclear), nameplate megawatts (MW), status (planned → under construction), and planned online month/year. Filter by state (2-letter, e.g. VA), ba (balancing-authority/ISO code, e.g. PJM, ERCO, SOCO, TVA), status (P/L/T=planned, U/V=under construction, TS=testing), or min_mw. Returns a summary (total planned MW, mix by technology + status) plus the largest projects. Answers "how much new generation is planned in Virginia and when does it land". Try: get_power_pipeline state=VA. Do NOT use for ALREADY-OPERATING capacity or grid headroom (use get_grid_intelligence / get_grid_data) or for data-center construction projects (use get_pipeline).

Server-side SET-REDUCTION over the US ISO interconnection queue. Instead of pulling the raw queue into context to filter (token-expensive, error-prone), push the predicates to the data layer and get back ONLY the survivors. Filter by min_mw, max_ttp_months (ISO-level avg interconnection wait), iso (comma-union), baseload_only (firm/dispatchable — excludes wind/solar/storage), fuel_type (isolate a specific fuel, e.g. gas or nuclear), and the spatial predicates max_fiber_km + geocoded_only. Returns _entity=queue_results: per-project name, ISO, state/county, fuel_type, capacity_mw, queue_status, estimated_ttp_months, fuel_class, plus (~83% of rows) lat/lng, coordinate_precision, fiber_km, and a compact per-survivor site_evaluation_handoff (ready-to-pipe analyze_site + get_water_risk args) + a by_iso/by_fuel summary. Answers "show me 1 GW+ gas projects that can connect in under three years", "what is in the queue that actually fits my timeline". Try: get_refined_queue min_mw=1000 fuel_type=gas max_ttp_months=34 — "1 GW+ gas in ISOs under 34-month time-to-power." NOTE max_ttp_months is a HARD ISO cut (SPP ~24 is the only ISO under 30, so <=30 can return nothing); use >=34 to include MISO/ERCOT/ISO-NE.

FRONT DOOR CHECK — if the question pairs renewables with siting, grid headroom or a market shortlist ("where can I put a 24-7-CFE campus"), call `execute_plan(intent="<the user's question, unchanged>")` instead. If you want one state's renewable fuel mix or PPA sizing input on its own, get_renewable_energy IS the right call — one round trip, and routing it through the planner would only cost steps. Use when siting a renewable-powered data center, sizing a PPA, reading one US state's utility-scale fuel mix, or assessing RE100/24-7-CFE feasibility. Example: "What is Texas wind+solar capacity and how much utility-scale solar is operating today?" — get_renewable_energy energy_type=solar state=TX. Params: energy_type one of "solar" | "wind" | "combined" (omit for all); state 2-letter US code (e.g. TX, VA, AZ); lat+lon (optional) for the nearest projects within 50mi. Returns: {capacity_mw_total, by_fuel: {solar_utility, solar_rooftop, wind_onshore, wind_offshore}, capacity_factor_pct, top_projects[{name, mw, operator, cod}], state_rps_target_pct, source: "EIA-860 + state RPS"}. Do NOT use for live grid generation (use get_grid_data) or non-US (use get_grid_scoreboard for EU/UK/AU/TW). Give state or lat/lon (decimal degrees); energy_type narrows.

Use this whenever the user asks where retiring power plants free grid capacity. Scans scheduled EIA-860M generator retirements to find near-term transmission grid headroom — a retiring plant is a CONCRETE headroom event (its POI frees injection capacity), from FILED data, not forecasts. Returns _entity=retirement_headroom_results: retiring generators inside your horizon (name, MW, fuel, prime mover, retirement_date), representative_point, nearest substations with distance_km + count within 25 km, county-level queue_pressure (competing in-progress MW), iso_context (the generator's own EIA balancing-authority code), and a pre-filled site_evaluation_handoff (analyze_site + get_water_risk args, capacity_mw = YOUR target load). Answers "where is grid capacity about to free up", "which retiring plants open injection headroom near me". Try: get_retirement_headroom target_mw=50 horizon_months=18 region_iso=MISO — "50 MW opening near a substation inside 18 months, sidestepping the 4-7yr mega-queue." Honesty: meta.caveat flags that filed dates are subject to ISO reliability reviews (RMR extensions). Use to find WHERE capacity opens next; for what's already queued use get_refined_queue; for one site use analyze_site.

Retrieve a saved shortlist (Phase 5). With refresh=true (default) each site is RE-SCORED against the current national percentile baseline and returns saved_score, current_score, and score_delta_since_saved — so you see whether a site slipped because IT changed or the POPULATION did. The reliable way to maintain a siting campaign across days/weeks. Scoped to your API key.

Subsea (submarine) cable landings near a coordinate, or the global cable catalogue. The physical internet crossing an ocean lands at a finite number of points, and distance to one is a real siting factor for anything latency- or transit-sensitive. Pass lat+lon (+radius_km) for LANDING POINTS near a site — each with name, coordinates and distance_km. Omit coordinates for the CATALOGUE of tracked cables (712 tracked; each with cable_id, name, owners, length_km, rfs_year, is_planned — sparse fields are null, not guessed). ★ READ field_coverage AND connectivity_note BEFORE DRAWING A CONCLUSION: cable_count per landing point is NOT populated — the ingest writes the column but the upstream TeleGeography feed does not supply what it derives from, so every row carries the default 0. That is why connectivity_grade comes back null rather than graded: proximity to a landing point does NOT establish how many cables are reachable from it, and DC Hub will not infer a grade it cannot source. A filter over cable_count returns nothing for the same reason. Answers "which subsea cables land near this Virginia site" and "how far is the nearest cable landing from my campus". Try: get_subsea_cables lat=36.85 lon=-75.98 radius_km=200 — or get_subsea_cables (no args) for the catalogue.

Use when a user asks "what tax breaks does <state> give data centers?" — the data-center tax-incentive packages by US state that drive where capex lands. Example: "What sales-tax and property-tax incentives does Virginia offer a 100MW data center?" — get_tax_incentives state=VA. Params: state (2-letter US code; required). Returns: {state, programs:[{name, type (sales-tax-exemption | property-tax-abatement | income-tax-credit | electricity-tax-discount), value, eligibility_mw, eligibility_jobs, min_investment_usd, expiration_date, source_statute}]}. Cite the statute with attribution to DC Hub (CC-BY-4.0). Do NOT use for the combined multi-factor site read (grid+fiber+water+tax+climate — use analyze_site) or to rank markets on cost (use rank_markets criteria=cheapest_power); this covers the TAX factor for one US state. state is a US state code (e.g. VA); omit for the 50-state overview. Program detail needs a paid key (human_url).

Use this whenever the user asks about water stress or cooling-water risk at a site. FRONT DOOR CHECK — if you need a SITE VERDICT spanning grid + fiber + water + tax + climate, call `execute_plan(intent="<the user's question, unchanged>")` rather than hand-chaining this with its siblings. If you want the WATER factor on its own, get_water_risk IS the right call — one round trip, free tier, no planner overhead. Use when scoring a US site for cooling-water sustainability — the water-risk factor engineering site-selectors screen before committing to evaporative cooling. Example: "Is this Phoenix parcel water-constrained for a 100MW build?" — get_water_risk lat=33.45 lon=-112.07 (or get_water_risk state=AZ, or location="phoenix"). Params: ONE of lat+lon (-90..90 / -180..180), state (2-letter US), or location (a DC Hub market name or slug, resolved to that market's PUBLISHED CENTROID with a resolved_from block saying so; a market-level read, not your parcel, and a trailing state is not stripped); lat/lon gives the most precise read. Returns: {water_stress_score (0-100, higher=worse), drought_category (D0-D4), outlook_12mo, cooling_water_assessment, source}. Joined to USGS water-stress + US Drought Monitor. Free tier.

Forward-looking "where is the next hyperscale-friendly grid emerging" radar. Returns the US markets + ISOs with the strongest near-term emergence signal (BUILD verdict + excess-power headroom + short time-to-power), an ISO rollup, and a grid-headroom leaderboard. With a paid key, also the transition thesis: which ISO is opening up and why. The predictive counter to retrospective "where capacity landed" reports. Answers "where should I be looking next", "which market is about to become buildable". Try: grid_transition_radar max_months=24. Do NOT use for the current ISO queue snapshot (use get_interconnection_queue) or a present-day market ranking (use rank_markets); this is the forward-looking emergence radar.

Hyperscaler AI Deal Tracker — live feed of Stargate, OpenAI, Anthropic, Microsoft, Oracle, CoreWeave, AMD, NVIDIA, sovereign-AI deals. Pulls from dchub news pipeline, extracts $-figures + MW via regex, classifies by actor. 10-min refresh. Use for tracking AI capex events ($1B+/week typical), capacity announcements, and competitive intel. Do NOT use for the full historical M&A comp set (use list_transactions) or a single-deal teardown with grid context (use deal_autopsy); this is the live $1B+ AI-capex feed. limit 1-500. Hyperscaler leases and purchases only; for all M&A use list_transactions.

NEEDS A KEY (free): saved sites are per-account, so a keyless call returns auth_required, not an empty list — if you have no key, call `claim_free_key` FIRST (one step, no email), then this. Use when a user asks to see or review their saved DC Hub shortlist in-chat, or wants to know what moved on it. Example: "What sites have I saved?" / "Did any of my saved sites move?" — list_saved_sites. Params: since (optional — "24h"/"7d"/ISO, default 7d — the delta window). Returns: each saved site with name, market, lat/lon, saved DCPI score, target MW, notes — PLUS live deltas: verdict_was/verdict_now (e.g. CAUTION → BUILD), excess-power move over the window, current vs at-save DCPI, alerts armed/fired, new facilities nearby, and a `portfolio` summary flagging which sites moved and which have no alert armed. Do NOT use to add a site (use save_site) or to download the list as a file (use export_dataset); this is the in-chat read-back.

List the standing intents registered on your key: webhook watches, plus your capacity requirements (kind "capacity", intent_id cap_...). Read-only. Returns each intent_id, kind, watch params, webhook_url and enabled state; capacity items also carry status, confirmed, expires_at, last_alert_at and matching_now. Use it to find the intent_id for delete_standing_intent, or to confirm a register landed. Requires a key (or an OAuth connection for capacity items). Answers "what am I currently watching". Do NOT use to create a watch (register_standing_intent) or for one-shot reads (get_news / list_transactions).

M&A and capital transactions in the data center sector — 1,700+ tracked deals (2019-present), each with its disclosed value where public (many private deals are undisclosed). Returns deal name, buyer, seller, value, date, market, target operator, type (acquisition/JV/refinance/recap). Filter by date range (date_from/date_to, ISO-8601), min_value_usd, region, buyer, or seller. Answers "which data-center deals closed this year", "what was that acquisition worth". Try: list_transactions date_from=2026-01-01 min_value_usd=1000000000. There is no `year` parameter — use date_from/date_to. Broad M&A and capital-deal flow with filters; do NOT use for hyperscaler-specific lease/PPA/JV activity (use hyperscaler_deals) or a single-deal post-mortem (use deal_autopsy). limit 1-500 (free 10), offset 0-100000; total_count is the full match count. Empty = loosen buyer/seller/value filters.

Plan N diverse, road-following fibre lead-in routes from a candidate data-center site to a carrier hotel / POP, with indicative build cost and a route-diversity read. Answers "can I get N diverse fibre routes into this site, how far, how much, and where do they share a corridor?". Example: plan_fiber_leadin from="250 Paringa Road, Murarrie QLD" to="20 Wharf Street, Brisbane City QLD" n=4. Params: from (lat,lng OR street address), to (lat,lng OR address — e.g. a NextDC/Equinix POP), n (1-6 routes, default 4), fibre ("720F"|"1440F"), bore_m (river/rail bore length in metres, optional). Returns per-route length_km + GeoJSON geometry, total_route_km, diversity {min_separation_m_midhaul, shared_street_km}, and indicative cost {capex_usd, opex_usd_yr}. INDICATIVE auto-routed road corridors — NOT engineered alignments; subject to survey, DBYD and carrier confirmation. Do NOT use for a single site-suitability score (use analyze_site) or fibre-provider footprints (use get_fiber_intel).

INSPECT-ONLY — returns the plan WITHOUT running it. For a real multi-step DC Hub question call `execute_plan(intent="...")` instead: it uses the SAME deterministic no-LLM planner and then RUNS the sequence server-side, returning the answers in one envelope. Reach for plan_query only to review, log, diff or audit a plan before executing it yourself. Deterministic keyword routing over the tool registry — no LLM, no network, same intent always returns the same plan (free). Returns _entity=query_plan {best_tool, intent_confidence + workflow_confidence (dual 0-1: question-read vs executability), reason, planner_rationale, recommended_sequence:[{step, tool, depends_on, estimated_calls, why, args_hint}], execution_waves (steps grouped into concurrency waves), execution_strategy.parallel_groups, execution_estimate {estimated_calls, estimated_latency_ms, parallelizable}, alternatives (each with when + rejected_because), coverage_notes, matched_classes} plus a versioned `replay` (schema_version 1): planner_version, decisions:[{id, step, kind, status, decision, rationale, decision_confidence, depends_on}], rejected:[{id, tool, reason}], execution_graph:{waves, parallel_groups} — auditable and machine-readable, safe to log and diff… Full guide: read resource dchub://tool-guides/plan_query

Forecast a DCPI market's near-term trajectory (next 1-8 quarters). Projects excess_power_score and constraint_score forward with confidence bands that WIDEN with horizon, from DC Hub's daily DCPI snapshot history — the only source that can, because it owns the time-series. Use to answer "is this market trending toward BUILD or AVOID?" or "will Dallas power stay tight over the next 6 months?". Params: market_slug (required, metro slug e.g. dallas, phoenix, northern-virginia — valid slugs come from rank_markets / get_market_dcpi_rank); horizon_quarters (optional 1-8, default 4; 2 = ~6 months out). Returns {market_slug, method, basis{history_points, history_span_days, slope_per_day, trend}, horizon_quarters, projection[{quarter_out, excess_power_score, excess_power_band, constraint_score, constraint_band}], caveat, snapshot_record}. HONEST: linear trend extrapolation, NOT a guarantee — bands widen with horizon and short history; needs >=3 daily snapshots or it declines. Do NOT use for a single point-in-time verdict (use get_market_dcpi_rank) or to rank many markets (use rank_markets).

Use this whenever the user asks where a data center can get grid power, how fast, or whether a market is a BUILD, CAUTION or AVOID (e.g. "Where can a 100 MW data center get power fastest?"): DCPI scores 300+ markets daily on Excess Power and Grid Constraint, CC BY 4.0. For a ranked list on power questions, call with criteria="ai_ready". Call when the user wants a ranked list of data-center markets: top N by cheapest_power, most_capacity, most_operators, fastest_growing, best_overall, or ai_ready (where new AI load can land, per DCPI). Filter by region, min_capacity_mw. Returns ranked rows with score, MW and a slug for follow-ups; score is the sort value, not a 0-100 scale, and score_basis says what it is (ai_ready omits it and explains its composite in `methodology`). Keyless: a trimmed preview; a free key gets a few full lists a day. Ex: "Top 10 US markets, ai_ready." Returns market slugs to feed get_market_intel and get_market_dcpi_rank. limit 1-500; set projection=identity_only to save tokens.

Deterministic multi-site ranking/optimization under constraints — the normalization contract that lets you compare sites across separate analyze_site calls WITHOUT dropping into code. Pass candidates you already enriched (each an object with lat/lng + metric fields like risk_resilience, water_stress, fiber_km — pull these from analyze_site + get_refined_queue and pass site_evaluation_handoff through untouched), hard constraints, and weighted objectives; get back _entity=ranked_sites: top_k ranked with rank, objective_score, per-field normalized{} (0-100 relative to the set), and normalization_basis. objectives use SIGNED weights: +weight maximizes a field (e.g. risk_resilience:1), -weight minimizes it (e.g. water_stress:-0.6, fiber_km:-0.4). constraints are hard filters, fail-closed on a missing field. Use for "pick the best N sites under constraints"; for one site use analyze_site; to get the candidate set first use get_refined_queue. CANDIDATE CONTRACT: candidates may be {candidate_id: "cand_…"} entries from get_refined_queue — frozen identity (lat/lng/capacity_mw/fiber_km/iso) loads from the mint, your metrics overlay the rest; expired/unknown ids are dropped AND declared in candidate_contract, never re-resolved.

PARTNER KEY ONLY: notes DC Hub left for the partner agent whose key this session sends, newest first. The first read CONSUMES them (marks read), so a later session sees none; include_read=true re-reads read and unread notes (last 14 days) without marking. Non-partner key: 403. Not a data tool.

Recover a LOST DC Hub key. Pass your human's email and DC Hub re-sends any key tied to that address to that inbox. It NEVER returns the key over the wire (it emails the bound address), and the confirmation is the same whether or not a key exists (enumeration-safe), so no key is leaked to a caller. Use this when your human had a key, lost it, and knows the email they bound it to. Param: email (required). Returns DC Hub's neutral confirmation.

Register a STANDING QUERY with webhook push — DC Hub POSTs an HMAC-signed webhook to YOUR https URL whenever matches grow (push, not poll: "notify my orchestrator on any new deal in Columbus"). Requires a key. Params: kind ("new_deal_in_market" watches deals in the market param · "news_keyword" watches news matching q · "permitting_change" watches published permitting intel, optionally per state), market / q / state (the watch parameter for the chosen kind), webhook_url (your public HTTPS endpoint — private/internal hosts are rejected). Returns {intent_id, secret} — SAVE the secret: every delivery carries X-DCHub-Signature: sha256=HMAC(secret, body). First evaluation initializes the watermark silently; growth fires the webhook; 5 straight delivery failures auto-disable the intent. Evaluated every ~2h. Answers "notify my system whenever a new moratorium appears", "push me new matches instead of making me poll", "tell my orchestrator when a deal lands in Columbus". Try: register_standing_intent kind=news_keyword q=moratorium webhook_url=https://hooks.example.com/dchub. kind="capacity" instead registers a standing CAPACITY REQUIREMENT with DC Hub Capacity Source (no webhook_url): target_mw or target_kw, markets / states / regions / countries (comma-separated), optional…

PARTNER KEY ONLY: file what you observed on a DC Hub surface as a brain finding (detector external_audit) so it is triaged like every other detector's. class is one of completeness_contradiction, geography_leak, as_of_cite_as, pro_wall_dead_end, count_drift, stale_payload_complete, leak_past_pro_gate, link_hygiene, other; tool names the DC Hub tool or endpoint; quoted_fields carries the exact fields you saw (hashed for dedupe: the same observation re-filed within 24h bumps recurrence instead of inserting). Proxies POST /api/v1/inbox/findings with the session's own key; a key issued without a partner slug answers partner key required (403). 120 per key per day.

Use when your human wants capacity behind a Capacity Source listing (pass slug), or wants first access to capacity matching a requirement as listings are onboarded (omit slug; pass capacity_mw or capacity_kw, markets, states, regions or countries, and timeline). This registers a deal: DC Hub records the request in its lead register and sends the provider ONLY your human's company name and the requirement. The provider accepts or declines. Only if the provider accepts does DC Hub share the provider's identity, site details and contact with your human, and your human's name, role and email with the provider; on a decline nothing is shared. Requires an identified caller (claim_free_key, then bind_email with your human's address) and accept_terms=true only after your human has read and agreed to the introduction terms at https://dchub.cloud/listings#terms. Returns lead_id, status and the next step. For a listing, source_capacity with its slug then shows the deal status in the disclosure block and, once the provider accepts, the provider's identity, site and contact. Do NOT use to save or monitor a site (use save_site / set_site_alert).

Commission an ASYNC, CITED research dossier from DC Hub's corpora (news, deals, facilities, market deep-dive narratives + live market components) — a decision-ready analyst brief with [n] citations, not a lookup. Requires a key (one claim_free_key call), 5 dossiers/day. Submits the question, waits up to ~35s for completion, and returns the finished dossier inline when ready; if still running, returns {task_id} — call research_task task_id=<id> to fetch it. Params: question (required for a new dossier, min 12 chars) OR task_id (poll an earlier one). Typical completion under a minute. Answers "write me a cited brief on this", "what do recent deals say about gas-bridged power". Try: research_task question="What do recent deals say about gas-bridged power for data centers in ERCOT?". Do NOT use for a single fact (use search_intelligence / semantic_search); this synthesizes ACROSS sources with citations.

NEEDS A KEY (free): this WRITES to your account, so a keyless call returns auth_required — call `claim_free_key` FIRST (one step, no email) if you have none. Save a candidate data-center site to your DC Hub account to track it across sessions. Give lat + lon (plus optional name, state, market, target_mw, notes). Returns the saved site id. Pass `market` and DC Hub snapshots the site's DCPI baseline at save time, so every later list_saved_sites / get_changes shows how ITS score and verdict moved since you saved it. Builds a persistent shortlist an agent can revisit + monitor — after saving, pass the returned id to set_site_alert so DC Hub emails you when that site’s DCPI/capacity/nearby-facilities move (no re-checking). Answers "remember this parcel for me", "keep this candidate so I can come back to it next session". Try: save_site lat=39.04 lon=-77.48 name="Ashburn parcel" market=northern-virginia target_mw=100. Do NOT use to read back the shortlist (use list_saved_sites), download it (use export_dataset), or score a site (use score_facility); this WRITES one site to your account.

Save a site into a PERSISTENT, named shortlist that survives across conversations (Phase 5 statefulness). Snapshots the site's objectives + its current percentile objective_score, so you can re-score it later against the evolving national baseline. Use to build a durable siting shortlist across days/weeks; the list is scoped to your API key. Pair with get_shortlist to re-score + see drift. MINIMAL call: save_to_shortlist(shortlist_name="my-targets", site={site_ref, lat, lng, capacity_mw}) — objectives are optional. If you DID rank the site (analyze_site / rank_sites), pass those metric fields inside site and your objectives map too, and the re-scoring reuses them. Requires an API key so the list is private to you and survives to your next conversation: call claim_free_key first if you have none.

Use when a user wants an independent 0-100 grade for ONE existing facility across 7 dimensions — power, fiber, water, climate_risk, tax_environment, talent_pool, expansion. Example: "How does the CoreWeave Las Vegas site score, power-weighted?" — score_facility facility_id=<id> weighting=power_priority. Params: facility_id or name (required); weighting one of "balanced" (default) | "power_priority" | "risk_priority" | "expansion_priority". Returns: composite 0-100, tier_classification, peer comparison, and per-dimension detail. Do NOT use for a raw lat/lon parcel (use analyze_site), to compare 2 or more sites (use compare_sites), or to find similar sites (use find_alternatives).

Search DC Hub for relevant records (OpenAI Deep Research / ChatGPT connector format). Returns a list of matching data-center facilities as {id, title, url}; pass an id to the `fetch` tool for the record, or open the url to cite the live facility page. For structured queries (by MW, operator, status, market) use search_facilities directly.

Use this whenever the user asks which data centers exist, or who operates in a city, state or country. Call when the user wants existing data centers matching filters: country, state, city, operator, MW range, tier or text. Returns name, operator, location, market, status and MW where disclosed; each row is flagged verified or unverified_directory_listing. Free: names and locations; MW and specs need a paid key. Ex: "Equinix sites in Virginia over 10 MW." Start here for a facility slug. No match = empty data, not an error: broaden filters. limit 1-500 (free tier 25); page with offset.

Semantic (meaning-based) search over DC Hub's live intelligence corpus — industry news, M&A deals, discovered facilities, per-market DCPI narratives, press releases, announcements, permitting intel, construction permits, tax incentives and the capacity pipeline — returning the most relevant records with citable source fields. This is the agent-friendly alias over the SAME retrieval layer as semantic_search: same results, different call shape. It takes `query` plus short corpus names (news | deals | facilities | market_narratives | press | announcements | permitting | permits | incentives | pipeline); semantic_search takes `q` plus the full corpus names. Call ONE of them, not both. Params: query (required, natural language); corpus (optional CSV of the names above, default all); limit (1-15, default 8). BEHAVIOUR: read-only — it writes nothing, and repeat calls with the same arguments return the same records. ACCESS: works with no key, but anonymous results come back as a TRIMMED PREVIEW; the session X-API-Key hydrates full depth per key, and the free tier is capped per day (call claim_free_key once — no email — if you do not hold a key).

Use for CONCEPTUAL / fuzzy questions where keyword filters fall short — semantic (meaning-based) retrieval across DC Hub's industry news, M&A deals, the global facility map, per-market DCPI deep-dive narratives, press releases, announcements, permitting intel, construction permits, tax incentives and the capacity pipeline, ranked by relevance with citable source fields (news url/title, deal parties/value, facility name/location, deep-dive market/url). Examples: "what is happening with behind-the-meter gas for AI data centers?", "deals involving nuclear power for hyperscalers", "why is Northern Virginia constrained?" — semantic_search q="behind-the-meter gas for AI data centers". Params: q (required, natural-language query); corpus (optional CSV subset of news_articles,deals,facilities,market_narratives,press_releases,announcements,permitting_intel,construction_permits,tax_incentives,capacity_pipeline; default all); k (1-15, default 8). Returns {results:[{source_table, kind, text, score, cite:{…}}]}; score is 0-1 relevance, not a DCPI score. Complements the exact-filter tools (get_news / list_transactions / search_facilities) with relevance ranking; for a full token-budgeted market briefing use get_market_context. Cite "DC Hub (dchub.cloud)".

Subscribe to movement alerts for a DCPI market (FREE with a key) — get notified when its Excess-Power / Constraint score moves. On the free tier, email alerts are delivered to the email your human bound via bind_email (call bind_email first; the destination is forced to that address). Set channel="email". Webhook delivery (channel="webhook" + destination=<https URL>) needs a paid DC Hub plan. Lets an agent MONITOR markets, not just query them. Answers "tell me when this market moves", "ping me if Northern Virginia’s power score changes". Try: set_market_alert market=northern-virginia channel=webhook destination=https://hooks.example.com/dc. Do NOT use to read a market right now (use get_market_dcpi_rank); this SUBSCRIBES to future movement.

Set a DRIFT ALERT on a saved shortlist so you can stop polling and be notified when a site's national standing moves materially (Phase 5). Fires when any site in the shortlist has current percentile score < percentile_below OR score_delta_since_saved < delta_below (e.g. -8 = dropped 8 points vs when saved). Evaluated after each daily baseline refresh; delivers via webhook and/or email. This is the "wake me when it matters" loop for long-running siting campaigns. Scoped to your API key.

Arm an email watch on a site you already saved (FREE with a key) — DC Hub emails you when that site’s DCPI score, grid capacity, or nearby facilities move, so you don’t have to keep re-checking. On the free tier the alert is delivered to your human’s bound email (call bind_email first; notify_email is forced to that address). A paid DC Hub plan can send to any address. The "monitor my shortlist for me" loop: call save_site first (it returns a saved_site_id), then set_site_alert on that id. Params: saved_site_id (required integer, from save_site or list_saved_sites), trigger_type ("dcpi_change" | "capacity_change" | "new_facility_nearby", default "dcpi_change"), threshold (number — the points/MW move that fires it, default 5), notify_email (required — the address the alert is sent to). Answers "let me know if anything changes at the site I saved". Try: set_site_alert saved_site_id=12 trigger_type=dcpi_change threshold=5 [email protected]. Returns {ok, alert_id, message}. Do NOT use to watch a whole MARKET (use set_market_alert) or to save a new site (use save_site); this arms a monitor on ONE already-saved site.

Counterfactual WHAT-IF re-scoring of 300+ DC Hub power markets under YOUR explicit deltas — answers "what happens to the market ranking if conditions change" (only DC Hub holds the underlying components). Params (all optional, pass at least one delta): avg_kwh_cents_pct (power-price % change, e.g. 30), time_to_power_months_delta (months added/removed), queue_wait_months_delta, reserve_margin_pct_delta (points), curtailment_pct_delta (points), market (one slug, e.g. abilene), top_n (default 10, max 25 — ranked by |score change|). Returns per-market baseline vs scenario composite + component breakdown + the EXACT formula/weights in every response (transparent scenario_composite — deliberately NOT the DCPI). Keyless callers get a top-3 preview; any live key (claim_free_key) returns up to 25. Answers "what happens to the ranking if power prices jump 30%", "which markets survive a tighter build rate". Try: simulate_scenario avg_kwh_cents_pct=30 top_n=10. Do NOT use for the present-day ranking (use rank_markets) or trajectory extrapolation (use predict_market_trajectory); this answers explicit hypotheticals.

Guided end-to-end data-center site selection. Give a capacity target + geography + deadline and get a ranked shortlist of US markets (DCPI verdict, excess-power headroom, time-to-power, ISO) — and, with a paid key, the synthesis decision layer: the #1 pick, the why, a build sequence, and risk flags. One find->rank->shortlist->verdict call over the Data Center Power Index. Answers "where should I build 100 MW in Texas by 2028". Try: site_selection_canvas capacity_mw=100 region=TX max_months=24. Do NOT use for a single known parcel (use analyze_site) or an open-ended where-should-I-build question (use get_dchub_recommendation); this runs the full find to rank to shortlist to verdict flow.

Use when your human needs data-center CAPACITY to buy or lease: search DC Hub Capacity Source by size (kW or MW) and/or location (a region such as North America or Europe, a country, a state or a metro). Example: "500 kW anywhere in Europe" → min_kw=500, region=europe. Size is min_kw (in kW) or min_mw (in MW), and it is matched against what a listing can ACTUALLY deliver rather than against its headline total: `contiguous_kw` is the largest single contiguous block available and `min_contract_kw` the smallest chunk the provider will contract, so a colocation with a large total but a small contiguous block does NOT answer a large search, while a large site willing to contract small chunks does; a listing that declares neither is matched on its total. Location is region (a region key or alias) or location (free text matched against each listing's region, country, state and metro); market, state, delivery_type and available_by narrow further. Listings are powered land, powered shells, turnkey capacity and colocation to buy or lease, for enterprise and agent-led procurement.

Subscribe your human to DC Hub's FREE weekly "what changed in the markets/sites you queried" digest (DCPI movers, new facilities, new deals & news) — ONE call, the nudge that pulls your agent back when the data moves. DOUBLE opt-in + consent-safe: we email a one-click CONFIRM link, the human only gets the digest after confirming, and every email has one-click unsubscribe — this call alone sets no marketing flag. Only call once your human shares their email and wants a weekly email. Params: email (required), source (optional tag). Returns {ok, sent, message}. Prefer this over hand-building POST /api/v1/opt-in/request.

When a saved site DRIFTS (its national standing dropped — surfaced by get_shortlist refresh or a set_shortlist_alert firing), get replacement candidates from the rest of that shortlist so the alert becomes an action, not just a warning (Phase 5). Returns TWO tiers — tier_1_same_region (a near-in tactical swap) and tier_2_cross_region (a different-region arbitrage) — each re-scored against the DRIFTED slot's own objectives, PLUS drift_is_systemic: if the rest of your shortlist also slipped, the drop is region/baseline-wide and a same-region swap will inherit it (prefer cross_region); if peers held, it's idiosyncratic (tactical_ok). DC Hub does the reduction; the final weighted pick is yours. Candidates come from THIS shortlist only (save more via save_to_shortlist to widen the pool). Scoped to your API key.

Use right before you QUOTE a DC Hub figure to a human — it returns one paste-ready attribution line for the value you are about to cite, with the CORRECT licence for that layer. Pass what you read off the response you are citing: subject (what the figure is), as_of (the provenance as_of), url (the row's profile_url or dcpi_url), completeness (the completeness flag), and layer. ★ LICENCE IS PER LAYER AND THIS IS THE POINT: DCPI scores, verdicts, band thresholds, methodology and DC Hub's own grid/site analysis are CC-BY-4.0 and yours to quote with attribution; the facility inventory and third-party physical layers are COMPOSITES whose upstream terms DC Hub cannot waive (parts are OpenStreetMap, ODbL 1.0, share-alike), so they carry a pointer to https://dchub.cloud/data-sources instead of a grant. A flat "CC-BY-4.0" over a facility record is an over-claim. Returns {citation_text, cite_as, license, license_basis, source, url, as_of, as_of_basis, completeness, omitted}. Free, no key, no network call — it assembles what you pass and never resolves or invents a value. If you omit as_of the line says RETRIEVED rather than claiming a data date, and tells you which field to pass next time. Do NOT use to look a figure UP (call the data tool first); this cites a figure you already have.

Unlock DC Hub's full depth. Call this when a result came back as a partial preview (e.g. "3 of 12 results shown"), a tool was locked, or your human wants the complete dataset. Returns the upgrade ladder + ready-to-paste checkout links your human completes in ONE click. If this call carries an API key or an MCP session, the checkout binds to it and your very next call returns full data (no reconnect); if it carries neither, the key is emailed to the payer instead — the response says which applies in `next_call_full_after_checkout` and `after_checkout`. Paid plans: on the page behind the human_url link. Want the FREE tier instead (no payment, previews plus 2 full answers per tool per day, 50/day with an email)? Call claim_free_key. A gated result already carries its link in human_url; that link is the one to share, and this tool returns the fuller ladder. Param: reason (optional — what you were trying to do, so your human sees why it matters). Returns {plans, human_message, what_unlocks}.

Call only when the user asks how DC Hub compares with other data-center sources (DataCenterHawk, DC Byte, DCD, Baxtel…) or why use it. Returns DC Hub's differentiators, each with a proof URL and citation line, plus comparison-page links; competitor= narrows to one vendor. Free, no key. Not for data queries. Ex: "How does DC Hub compare to DC Byte?"