Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

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

REMOTE · DCHUB.CLOUD · 3 COMPONENTS

DCPI grid-power scores for 300+ markets, plus capacity to buy or lease; query and cite.

+9 this week 82 Trust /100

Last scanned (20 hours ago)

Scores higher than 88% of remote servers

Reachable. Last reached 16 Oct 2026.

Category Cloud Infrastructure

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability80
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 13173 tokens (~196/item across 67 items; 67 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management55
  • Stability check failed: schema churn in the 17 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_plan" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 68 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
  • 14 Oct 26 +1
    • Server version: 2.12.36 → 2.12.37 functional
  • 12 Oct 26 0
    • Server version: 2.12.34 → 2.12.36 functional
  • 11 Oct 26 +7
    • Stability: 0.17 → fail ▼ security
    • Tool “research_task” was removed ▼ security
    • HSTS header: fail → pass ▲ security
    • DNSSEC: fail → pass ▲ security
    • Server version: 2.12.30 → 2.12.34 functional
  • 4 Oct 26 +1
    • Server version: 2.12.26 → 2.12.27 functional
    • Server version: 2.12.25 → 2.12.26 functional
    • Server version: 2.12.24 → 2.12.25 functional
    • “source_capacity” added an optional parameter “max_sites” cosmetic
    • “get_water_risk” added an optional parameter “location” cosmetic
    • “source_capacity” added an optional parameter “max_providers” cosmetic
    • “source_capacity” added an optional parameter “min_chunk_kw” cosmetic
    • “source_capacity” added an optional parameter “target_kw” cosmetic
    • “source_capacity” added an optional parameter “target_mw” cosmetic
    • “source_capacity” reworded the description of “available_by” cosmetic
  • 2 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Sept 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 29 Sept 26 71

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 16 Oct 2026 · Probed https://dchub.cloud/mcp/claude

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=dchub.cloud CN=WE1,O=Google Trust Services,C=US 11 Oct 2026 9 Jan 2027 ECDSA 256 ECDSA-SHA256 7cadce02bd1e9275139023d74dbd768c
SANs: dchub.cloud
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of dchub.cloud. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
cloud. present 7041 13 Verified
dchub.cloud. present 2371 13 Verified
dchub.cloud. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=15552000
content-security-policy default-src 'none'; frame-ancestors 'none'
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://dchub.cloud/mcp/claude Verified 200
http (plaintext) http://dchub.cloud/mcp/claude HTTPS enforced 301 https://dchub.cloud/mcp/claude
MCP tools · 67 exposed · ~12,966 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ai_capacity_index ~82

Rank data-center markets by where large AI training capacity could land in the next 30, 60 or 90 days, with facility and operator counts.

NameTypeReqDescription
horizoninteger–Deployment horizon in days: 30, 60, or 90 (default 90)
limitinteger–Number of top markets to return (default 20)

No output schema declared.

No examples provided.

analyze_parcel ~218

Analyze a parcel boundary (GeoJSON, or lat/lon in a hosted county) for acreage, shape and nearby infrastructure.

NameTypeReqDescription
capacity_mwnumber–Optional target load in MW to pass through into the site_evaluation_handoff
geometry––GeoJSON Polygon or MultiPolygon parcel boundary, e.g. {"type":"Polygon","coordinates":[[[lng,lat],[lng,lat],...]]} — a MultiPolygon carries discontinuous parcels as one envelope. Omit to look up the…
latnumber–Latitude of a point ON the parcel — used with lon when geometry is omitted to look up the containing parcel from the hosted county/state GIS layer
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Longitude of a point ON the parcel (used with lat when geometry is omitted)
longitudenumber–Alias for lon — either name works

No output schema declared.

No examples provided.

analyze_site ~467

Score one site (lat/lon, a candidate_id from get_refined_queue, or a market name) for data-center suitability: 0-100 overall score with power, gas, fiber, market and risk sub-scores and the nearby infrastructure behind them. Needs a DC Hub account with site-analysis access; without one it returns only a notice.

NameTypeReqDescription
candidate_idstring–PREFERRED for queue survivors: a cand_… id from get_refined_queue — coordinates come from the FROZEN mint (lat/lon args are ignored; zero transcription drift; expired ids fail closed with candidate_e…
capacity_mwnumber–Target power load for the build in megawatts (MW), e.g. 100 (typical 50-500)
include_fiberboolean–Include fiber-connectivity analysis (default true)
include_gridboolean–Include grid-headroom / substation analysis (default true)
include_riskboolean–Include water/drought/climate risk analysis (default true)
latnumber–Site latitude in decimal degrees (-90 to 90; required unless candidate_id or location given), e.g. 33.45
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
locationstring–Market NAME or metro slug instead of coordinates, e.g. "ashburn", "northern-virginia", "dallas". Resolved to that market's PUBLISHED CENTROID through the DCPI market row, and the answer carries a res…
lonnumber–Site longitude in decimal degrees (-180 to 180; required unless candidate_id or location given), e.g. -112.07
longitudenumber–Alias for lon — either name works
statestring–US state abbreviation (optional) — improves the tax-incentive lookup, e.g. AZ

No output schema declared.

No examples provided.

cluster_sites_by_latency ~257

Group 2-8 sites into low-latency clusters using physics-bound round-trip time floors between each pair.

NameTypeReqDescription
candidate_ids––Array (or comma-separated string) of candidate_id values from get_refined_queue — each resolves to its FROZEN mint coordinates (zero transcription drift); expired/unknown are dropped and declared in…
max_latency_usnumber–Round-trip latency budget in microseconds (default 1000 µs = 1 ms; sync replication is typically 1000-2000 µs)
min_confidencestring–Minimum evidence tier a pair must meet to count as viable: "published" | "tracked" | "inferred" (default inferred = include all)
sitesstring–Semicolon-separated "lat,lon" pairs, 2-8 sites (same format as compare_sites locations); optional per-site labels via "lat,lon:label", e.g. "39.04,-77.48:ashburn;39.29,-76.61:baltimore". cand_… token…

No output schema declared.

No examples provided.

compare_isos ~114

Compare 2-4 US ISO grids side by side (comma-separated, e.g. "PJM,ERCOT"): fuel mix, demand, renewable and gas share, queue depth and time to power.

NameTypeReqDescription
isosstringyesComma-separated list of 2-4 US ISO/RTO grid regions to compare, e.g. "PJM,ERCOT,CAISO" (valid: ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISONE)

No output schema declared.

No examples provided.

compare_sites ~172

Compare 2-4 candidate sites (semicolon-separated "lat,lon" pairs) side by side on the analyze_site scores, and name the highest-scoring one with the reason. Needs a DC Hub account with site-analysis access; without one it returns only a notice.

NameTypeReqDescription
capacity_mwnumber–Target power load for the build in megawatts (MW), e.g. 50 (typical 50-500)
locationsstring–Semicolon-separated list of 2-4 "lat,lon" pairs to compare, e.g. "33.45,-112.07;39.04,-77.48"
sites––Alternative to locations: an array of {lat, lon} (or {lat, lng}) objects, 2-4 sites

No output schema declared.

No examples provided.

deal_autopsy ~98

List recent data-center deals with the DCPI verdict and time to power of each deal's market.

NameTypeReqDescription
comparablesstring–Comparables detail: "none" (default — count only, cheapest), "summary" (top-2 grounding signals), or "full" (the complete cited set). Escalate only for deals you're drilling into.
limitinteger–Number of recent deals to return (default ~15)

No output schema declared.

No examples provided.

discover_tools ~74

List DC Hub tools grouped by family (facility, market, grid and power, gas, site, fiber, deals and news), optionally filtered by a query.

NameTypeReqDescription
querystring–Optional keyword to filter families/tools, e.g. "site selection", "grid queue", "fiber", "deals", "market"

No output schema declared.

No examples provided.

execute_plan ~454

Answer a multi-part data-center infrastructure question in one call. Pass the question as intent; a rule-based planner (no AI model) uses the text to choose the lookups (markets, grid, fiber, water, incentives), runs them, and returns each step's result with a replay of how the answer was built. Logging: the intent text is stored in DC Hub's usage log with the call (up to 4,000 characters, with the time, client name, IP address and API key if one is used) and in a plan-run record (first 500 characters). These records have no automatic deletion date. Privacy policy: https://dchub.cloud/privacy

NameTypeReqDescription
capacity_mwnumber–Target capacity in MW, e.g. 100.
context––Optional structured hints AND step-arg overrides: {lat, lon, iso, market, capacity_mw, candidate_id, state, since} — user-supplied values beat minted ones. The typed top-level params below are merged…
intentstringyesThe user's infrastructure question, passed through UNCHANGED. Examples: "rank markets for a 200 MW AI campus" · "evaluate 100 MW power headroom for a GPU training cluster in PJM" · "compare Dallas vs…
isostring–ISO/RTO code to pin geography, e.g. "PJM", "ERCOT".
latnumber–Latitude for a specific site.
lonnumber–Longitude for a specific site.
marketstring–Metro slug or name to pin the analysis to, e.g. "ashburn". Beats any market the planner would mint.
max_fanout––Max per-finalist fan-out calls for one step, 1-3 (default 2)
max_steps––Max plan steps to execute, 1-8 (default 6)
statestring–US state code, e.g. "VA".

No output schema declared.

No examples provided.

fetch ~75

Fetch one DC Hub facility record by an id returned from search. Returns {id, title, text, url, metadata} with name, operator, location, status and market.

NameTypeReqDescription
idstringyesA facility id/slug from a prior `search` result, e.g. equinix-dc1-ashburn

No output schema declared.

No examples provided.

find_alternatives ~153

Find facilities similar to a given facility nearby, with similarity scores and key differences.

NameTypeReqDescription
exclude_operatorboolean–If true, exclude facilities from the same operator as the seed
facility_idstringyesThe seed facility id/slug (required) to find alternatives to, from a prior search result — there is no `name` param; an undeclared key is silently stripped
limitinteger–Max results to return (1-500; default varies by tool)
match_onstring–Optional similarity dimension to weight, e.g. capacity, operator, fiber, market
radius_kmnumber–Search radius in km for candidate alternatives around the seed facility

No output schema declared.

No examples provided.

find_sites ~391

Find candidate data-center sites in a state or around a point, filtered by substation voltage and distance to gas and fiber.

NameTypeReqDescription
cluster_kmnumber–Collapse anchors within this many km into one candidate area (default 8, max 100). Raise it for broader coverage, lower it for denser results
exclude_moratoriumboolean–true = drop candidates in a state with a published data-center moratorium. STATE grain, not jurisdiction grain
latnumber–Latitude of a search centre, e.g. 39.04 — use with lon (+ radius_km) instead of state
latitudenumber–Alias for lat — either name works
limitinteger–Max results to return (1-500; default varies by tool)
lngnumber–Alias for lon — either name works
lonnumber–Longitude of a search centre, e.g. -77.48
longitudenumber–Alias for lon — either name works
max_fiber_kmnumber–Drop candidates farther than this from the nearest fiber route (CHORD approximation — see fiber_distance_basis). Applied ONLY if the fiber layer answers
max_gas_kmnumber–Drop candidates farther than this from the nearest gas pipeline. Applied ONLY if the gas layer answers — check constraint_coverage
min_voltage_kvnumber–Only anchor on substations at or above this voltage in kV (default 115). 230+ for hyperscale, 500 for the largest campuses
radius_kmnumber–Search radius in km around lat/lon (default 80, clamped 5-400); ignored in state mode
statestring–2-letter US state to search, e.g. OH — required unless you pass lat + lon

No output schema declared.

No examples provided.

generate_site_analysis ~299

Build a multi-page Site Analysis PDF for one lat/lon (power and transmission, gas, water, air permitting, fiber, latency, market, tax) and return its survey data and a download link valid for about 7 days. Needs a DC Hub account with site-analysis access; without one it returns only a notice.

NameTypeReqDescription
capacity_mwnumber–Target power load for the build in megawatts (MW), e.g. 150 (typical 50-500)
latnumber–Site latitude in decimal degrees (-90 to 90, required), e.g. 37.694
latency_targetstring–Optional metro to measure latency against; default = nearest real carrier hotel
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Site longitude in decimal degrees (-180 to 180, required), e.g. -88.65
longitudenumber–Alias for lon — either name works
prepared_bystring–Your firm name that brands the report; defaults to DC Hub, e.g. "Martone Advisors"
prepared_forstring–Client name printed on the report cover, e.g. "TON Infrastructure"
use_casestring–Optional workload descriptor to tailor the report, e.g. "AI training campus"

No output schema declared.

No examples provided.

get_backup_status ~31

Get per-feed freshness for DC Hub's data ingest: health, record count and refresh interval for each feed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_changes ~90

List what changed in DC Hub since a timestamp: DCPI market movers, newly found facilities, new deals and news.

NameTypeReqDescription
limitinteger–Max results to return (1-500; default varies by tool)
sincestring–Return changes since this ISO-8601 timestamp (YYYY-MM-DD or full datetime) or shorthand "24h"/"7d"; default 24h

No output schema declared.

No examples provided.

get_climate_intel ~168

Get seismic design values (USGS ASCE 7) and climate normals (NOAA) for a lat/lon, such as cooling degree-days and temperature extremes.

NameTypeReqDescription
latnumber–Site latitude in decimal degrees (-90 to 90, required), e.g. 33.45
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Site longitude in decimal degrees (-180 to 180, required), e.g. -112.07
longitudenumber–Alias for lon — either name works
radius_kmnumber–Max distance (km) to snap to the nearest NOAA station (optional, default 25)

No output schema declared.

No examples provided.

get_composite_site_score ~196

Score one lat/lon 0-100 using only measured factors (power and grid, fiber, natural-hazard risk, water), with a BUILD/CAUTION/AVOID verdict and a coverage map of which factors were measured. Needs a DC Hub account with site-analysis access; without one it returns only a notice.

NameTypeReqDescription
latnumber–Site latitude in decimal degrees (-90 to 90, required), e.g. 33.45
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Site longitude in decimal degrees (-180 to 180, required), e.g. -112.07
longitudenumber–Alias for lon — either name works
statestring–US state abbreviation (optional) — improves water/context lookups, e.g. AZ

No output schema declared.

No examples provided.

get_disaster_risk ~141

Get natural-hazard risk for a US lat/lon from the FEMA National Risk Index: flood, wildfire, hurricane, earthquake, heat, drought, tornado and more.

NameTypeReqDescription
latnumber–Site latitude in decimal degrees (-90 to 90, required), e.g. 33.45
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Site longitude in decimal degrees (-180 to 180, required), e.g. -112.07
longitudenumber–Alias for lon — either name works

No output schema declared.

No examples provided.

get_energy_prices ~106

Get energy prices by US state or ISO: retail electricity, wholesale and natural gas.

NameTypeReqDescription
data_typestring–Optional price type focus, e.g. retail, wholesale, gas
isostring–ISO/RTO grid region (required for ISO pricing): ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISONE
statestring–US state abbreviation for state-level pricing context, e.g. TX

No output schema declared.

No examples provided.

get_facility ~201

Get details for one data-center facility by id, slug or name: operator, address, coordinates, power capacity, cooling, fiber carriers, status, its market's DCPI verdict and nearby facilities.

NameTypeReqDescription
facility_id––Facility id from a prior search_facilities/search result (numeric or string), e.g. equinix-dc1-ashburn
id––Alias for facility_id — a facility id/slug from a prior search result
include_nearbyboolean–Include peer facilities near this one in the response (default true)
include_powerboolean–Include power capacity detail (total/used MW) in the response (default true)
namestring–Facility name as a fallback lookup when no id/slug is known, e.g. "QTS Ashburn"
slugstring–Facility slug from a prior search result, e.g. digital-realty-iad8

No output schema declared.

No examples provided.

get_facility_risk_delta ~112

Show how a facility's market DCPI health changed over a time window, with direction (improving, worsening or flat).

NameTypeReqDescription
facility_idstring–A DC Hub facility id or canonical slug to resolve the market context
marketstring–Alternatively, a market name or slug (e.g. "northern-virginia")
sincestring–Look-back window, e.g. "7d" or "30d" (default 7d)

No output schema declared.

No examples provided.

get_fiber_intel ~175

Get fiber route intelligence by carrier, route type or market: long-haul and metro routes and dark-fiber availability.

NameTypeReqDescription
carrierstring–Fiber carrier to filter on, e.g. Zayo, Lumen, Cogent, "Crown Castle", Windstream, GTT, Uniti; omit for all carriers
include_sourcesboolean–Include upstream data-source/provenance metadata in the response
marketstring–Metro name or slug (e.g. "dallas", "ashburn", "northern-virginia") — returns only routes touching that metro (either endpoint within ~1.2°). Great with route_type=longhaul.
route_typestring–Route class: "metro", "longhaul", "dark", or "ix"

No output schema declared.

No examples provided.

get_fiber_readiness ~162

Assess fiber readiness for a lat/lon: distance to a carrier-served facility, number of reachable carriers, and single-carrier risk.

NameTypeReqDescription
latnumber–Site latitude in decimal degrees (-90 to 90, required), e.g. 39.04
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Site longitude in decimal degrees (-180 to 180, required), e.g. -77.48
longitudenumber–Alias for lon — either name works
radius_kmnumber–Search radius in km for reachable fiber carriers (default 50, range 5-200)

No output schema declared.

No examples provided.

get_gas_index ~167

Get the Data Center Gas Index (DCGI): a per-US-state natural-gas suitability score for gas-fired or behind-the-meter power.

NameTypeReqDescription
limitinteger–Max results to return (1-500; default varies by tool)
statestring–US state abbreviation, e.g. TX, VA, AZ. Returns the DCGI score and verdict, plus `gas_price_series` naming which EIA series priced the state. A state that cannot be priced comes back verdict UNSCORED…

No output schema declared.

No examples provided.

get_global_power ~203

List power plants and generating units worldwide (operating and pipeline, all fuels) from the Global Energy Monitor tracker. Filter by country, fuel, status, area or size.

NameTypeReqDescription
bboxstring–Viewport filter as minLng,minLat,maxLng,maxLat
countrystring–Country/area name to filter, e.g. Germany, India, Brazil, Japan
fuelstring–Fuel/type filter, comma-separated for a union: coal, oil/gas, nuclear, solar, wind, hydro, bioenergy, geothermal
limitinteger–Max results to return (1-500; default varies by tool)
min_mwnumber–Minimum unit capacity in MW
pipelineboolean–true = ONLY the forward pipeline (announced + pre-construction + under-construction)
statusstring–Status substring filter, e.g. operating, construction, pre-construction, announced

No output schema declared.

No examples provided.

get_grid_data ~118

Get real-time grid data for one of the 7 US ISOs from EIA hourly data: fuel mix, demand and the 24-hour demand curve.

NameTypeReqDescription
isostring–ISO/RTO grid region (required): ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISONE
metricstring–Optional metric focus, e.g. fuel_mix, demand, demand_curve
periodstring–Optional time window for the metric, e.g. 24h

No output schema declared.

No examples provided.

get_grid_intelligence ~273

Get a grid brief for one US ISO: demand, fuel mix, excess-power and constraint score bands, interconnection queue and time to power.

NameTypeReqDescription
isostring–Alias for region_id — the ISO/RTO or balancing-authority code
marketstring–Market NAME or metro slug instead of a grid code, e.g. "Ashburn", "northern-virginia", "dallas". Resolved to its ISO through the published DCPI market row before the brief is built; the answer carrie…
regionstring–Alias for region_id — the ISO/RTO or balancing-authority code
region_idstring–Grid region (required): one of the 7 US ISOs (PJM, ERCOT, CAISO, MISO, SPP, NYISO, ISO-NE), an EIA balancing-authority code (e.g. SOCO, DUK, AZPS, TVA), or the PJM Dominion zone region_id="PJM-DOM" f…

No output schema declared.

No examples provided.

get_grid_scoreboard ~47

Get a live scoreboard of grid operators in the US, Great Britain, Europe and parts of Asia-Pacific and Latin America: demand, fuel mix, renewable share and gas share right now.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_hosting_capacity ~368

Get utility-published feeder hosting capacity near a location or in a market: the MW named distribution feeders can accept, from utility GIS data.

NameTypeReqDescription
capacity_typestring–Restrict to one published type: "load" (what a new data-center load can DRAW — the type that answers siting), "gen" (DER/generation EXPORT headroom — NOT available load), or "bus_headroom" (transmiss…
latnumber–Latitude of the point to search around, decimal degrees. Must be paired with lon.
latitudenumber–Alias for lat — either name works
limitinteger–Max results to return (1-500; default varies by tool)
lngnumber–Alias for lon — either name works
lonnumber–Longitude of the point to search around, decimal degrees. Must be paired with lat.
longitudenumber–Alias for lon — either name works
marketstring–Alias for utility — either name works (e.g. "Northern Virginia · Richmond", "New York City · Westchester").
min_mwnumber–Only return feeders whose published capacity is at or above this many MW.
radius_kmnumber–Search radius in km around lat/lon (default 25, max 150). Ignored when utility/market is passed — that mode covers the utility's entire published extent.
utilitystring–Utility or market name, case-insensitive substring — e.g. "Ameren Illinois", "Con Edison", "Providence". Searches that utility's whole published territory instead of a point radius. Call with NO argu…

No output schema declared.

No examples provided.

get_infra_projects ~384

List planned, approved and under-construction gas pipeline and transmission line projects. Filter by type, state, status, capacity, voltage and in-service dates.

NameTypeReqDescription
in_service_afterstring–Only projects entering service on or after this date (YYYY-MM-DD or YYYY). Gas compares the in-service year; transmission the actual, else projected, in-service date
in_service_beforestring–Only projects entering service on or before this date (YYYY-MM-DD or YYYY)
include_delistedboolean–Also return projects the latest source release no longer lists (completed, withdrawn or dropped). Default false
limitinteger–Max results to return (1-500; default varies by tool)
min_capacitynumber–Gas only: minimum pipeline capacity in million cubic feet per day (MMcf/d), e.g. 1000. With type=all it narrows to gas projects
min_kvnumber–Transmission only: minimum voltage in kilovolts (kV), e.g. 345. With type=all it narrows to transmission projects
new_sincestring–Only projects DC Hub first saw on or after this date (YYYY-MM-DD). The initial backfill is never counted as new
statestring–US state abbreviation, e.g. TX or LA. Gas projects match any state they cross; transmission projects are all TX
statusstring–Status, case-insensitive; comma list allowed. Gas: Announced, Pre-applied, Applied, Approved, Construction, On Hold, Completed. Transmission: Planned, Conceptual, Under Construction, Completed, Cance…
typestring–Which project list: gas_pipeline (EIA, US-wide), transmission (ERCOT TPIT, Texas only) or all (default)

No output schema declared.

No examples provided.

get_infrastructure ~226

List infrastructure near a location: substations, transmission lines, gas pipelines and power plants, with distance and capacity.

NameTypeReqDescription
latnumber–Center latitude in decimal degrees (-90 to 90, required), e.g. 33.45
latitudenumber–Alias for lat — either name works
layerstring–Optional single asset layer to return, e.g. substations, transmission, pipelines, power_plants
limitinteger–Max results to return (1-500; default varies by tool)
lngnumber–Alias for lon — either name works
lonnumber–Center longitude in decimal degrees (-180 to 180, required), e.g. -112.07
longitudenumber–Alias for lon — either name works
min_voltage_kvnumber–Only include transmission/substations at or above this voltage in kV, e.g. 69
radius_kmnumber–Search radius in kilometers around the point, e.g. 25

No output schema declared.

No examples provided.

get_intelligence_index ~42

Get a composite 0-100 health index for a data-center market, combining supply and demand, vacancy, absorption, fiber, power availability and pricing trend.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_interconnection_queue ~82

Get the interconnection queue snapshot per US ISO: queued generation capacity, and for ERCOT the large-load (data-center) queue.

NameTypeReqDescription
isostring–ISO/RTO grid region to drill into: ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISONE; omit for the all-ISO snapshot

No output schema declared.

No examples provided.

get_iso_context ~115

Get a token-budgeted briefing for one US ISO/RTO: live grid snapshot, DCPI verdicts across its markets, queue depth, benchmark prices and tracked markets.

NameTypeReqDescription
isostringyesISO/RTO grid region (required): ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISONE
max_tokensnumber–Token budget for the pack, 200-8000 (default 4000); sections are filled in priority order until the budget is spent

No output schema declared.

No examples provided.

get_market_context ~123

Get a token-budgeted briefing for one data-center market: DCPI verdict, power and grid facts, outlook, deals, pipeline, operators, risks and news, each section timestamped.

NameTypeReqDescription
marketstringyesMarket slug (required), e.g. northern-virginia, dallas, phoenix — valid slugs come from rank_markets / get_market_dcpi_rank
max_tokensnumber–Token budget for the pack, 200-8000 (default 4000); sections are filled in priority order until the budget is spent

No output schema declared.

No examples provided.

get_market_dcpi_rank ~91

Get the DC Hub Power Index (DCPI) read for one market: BUILD/CAUTION/AVOID verdict, score bands, time to power, data basis and a short analyst narrative.

NameTypeReqDescription
market_slugstringyesMarket slug (metro), e.g. northern-virginia, dallas, phoenix — valid slugs come from rank_markets / get_market_dcpi_rank

No output schema declared.

No examples provided.

get_market_intel ~150

Get market intelligence for one data-center market (by market slug): vacancy, capacity pricing, supply pipeline, main operators and growth.

NameTypeReqDescription
compare_tostring–Optional second market slug to compare against, e.g. dallas
marketstring–Market slug (metro), e.g. northern-virginia, dallas, frankfurt, singapore — valid slugs come from rank_markets / get_market_dcpi_rank
metricstring–Optional single metric to focus on, e.g. vacancy, pricing, absorption, pipeline
periodstring–Optional time window for the metric, e.g. ttm, 12mo, ytd

No output schema declared.

No examples provided.

get_metro_fiber ~99

Get the fiber profile of a US data-center metro: carriers, route miles, on-net buildings, fiber-density score, exchanges and carrier hotels.

NameTypeReqDescription
marketstring–Optional metro name or slug for a single-market deep dive (carrier-by-carrier + dark fiber), e.g. "Dallas-Fort Worth", "dallas", "Northern Virginia", "ashburn". Omit to list every tracked metro ranke…

No output schema declared.

No examples provided.

get_news ~193

Get curated data-center industry news. Filter by keyword, category, source and date range.

NameTypeReqDescription
categorystring–News topic filter, e.g. deals, permits, outages, policy, AI
date_fromstring–Earliest published date, ISO-8601 (YYYY-MM-DD)
date_tostring–Latest published date, ISO-8601 (YYYY-MM-DD)
limitinteger–Max results to return (1-500; default varies by tool)
min_relevancenumber–Minimum relevance score 0-1 to include an item, e.g. 0.5
querystring–Free-text keyword to filter news, e.g. "Stargate" or "interconnection queue"
sourcestring–Restrict to one trade source, e.g. DCD, "Data Center Frontier", "Capacity Media"

No output schema declared.

No examples provided.

get_peering_intel ~156

Get internet-exchange and peering density near a lat/lon from PeeringDB, or the top peering facilities overall.

NameTypeReqDescription
latnumber–Latitude of the site, e.g. 39.04 — with lon, returns the peering profile around it; omit both for the IXP directory
latitudenumber–Alias for lat — either name works
limitinteger–Max results to return (1-500; default varies by tool)
lngnumber–Alias for lon — either name works
lonnumber–Longitude of the site, e.g. -77.48
longitudenumber–Alias for lon — either name works

No output schema declared.

No examples provided.

get_permitting_intel ~92

List data-center permitting and moratorium records by jurisdiction: moratoriums, zoning restrictions, tax changes and utility pauses, each stage-tagged with a source.

NameTypeReqDescription
classstring–Record class: "moratorium" | "zoning" | "tax" | "utility_pause" (optional)
statestring–US state filter, e.g. NY or MN (optional)

No output schema declared.

No examples provided.

get_pipeline ~208

List data centers that are announced, permitted or under construction. Filter by status, country, operator, minimum capacity or expected completion date.

NameTypeReqDescription
countrystring–ISO 3166-1 alpha-2 country code, e.g. US, DE, SG
expected_completion_beforestring–Only projects with expected commissioning before this ISO-8601 date (YYYY-MM-DD), e.g. 2027-01-01
limitinteger–Max results to return (1-500; default varies by tool)
min_capacity_mwnumber–Minimum project power capacity filter in megawatts (MW), e.g. 50 for hyperscale
offsetinteger–Pagination offset, 0-based (skip this many results)
operatorstring–Operator/provider company name, e.g. Equinix, Digital Realty, AWS
statusstring–Pipeline stage filter: announced, permitted, construction, or operational

No output schema declared.

No examples provided.

get_power_availability_timeline ~143

Show year by year when power gets easier in one US state: new generation by confidence class, scheduled retirements, and interconnection-queue depth.

NameTypeReqDescription
mwnumber–Optional target MW for CONTEXT ONLY — echoed back with an explicit note; never converted into an energize-by date, which this data cannot honestly state
statestringyes2-letter US state code (required), e.g. OH, GA, TX — the timeline grain; a state can span ISOs and the response reports ISO membership as context
yearsnumber–Window in years from now, 1-6 (default 5)

No output schema declared.

No examples provided.

get_power_pipeline ~160

List planned and under-construction US power generators from EIA-860M, including non-ISO regions. Filter by state, balancing authority, status or minimum MW.

NameTypeReqDescription
bastring–Balancing-authority / ISO code, e.g. PJM, ERCO, SOCO, TVA, AZPS
limitinteger–Max results to return (1-500; default varies by tool)
min_mwnumber–Minimum nameplate capacity filter in megawatts (MW)
statestring–US state abbreviation to filter generators, e.g. VA, TX
statusstring–Generator status code: P/L/T (planned), U/V (under construction), TS (testing)

No output schema declared.

No examples provided.

get_refined_queue ~642

Filter the US ISO interconnection queue server-side by size, wait time, ISO, fuel, status, fiber distance and geocoding, and return only matching projects.

NameTypeReqDescription
baseload_onlyboolean–Keep only firm/dispatchable fuel (nuclear, gas, steam, geothermal, hydro, coal); exclude wind/solar/storage. Firm-vs-intermittent split only — does NOT sub-divide peaker vs combined-cycle gas (no dut…
developerstring–ERCOT only: keep projects whose developer name contains this text (case-insensitive substring, e.g. 'tenaska'). Developer names come from ERCOTQueue (ercotqueue.com, Matt Prusak, CC BY 4.0) joined to…
fuel_typestring–Isolate a fuel by inclusive substring match on the raw label; comma/semicolon-separated for a union, e.g. 'gas' hits GAS/Natural Gas, 'nuclear,hydro' unions both. Runs the fuel filter server-side ins…
geocoded_onlyboolean–Keep only survivors that carry lat/lng (~83% of the queue) — the ones with a ready site_evaluation_handoff you can pipe into analyze_site. Default false
isostring–Restrict to one or more ISOs, comma-separated for a union: PJM, ERCOT, MISO, CAISO, SPP, NYISO, ISONE (ISO-NE). e.g. iso=ERCOT,PJM. Omit for all; combines with max_ttp_months as an intersection
limitinteger–Max results to return (1-500; default varies by tool)
max_fiber_kmnumber–Keep only survivors within N km of the nearest MAPPED long-haul fiber route endpoint — coarse backbone proximity from a sparse ~260-node dataset over a county-centroid origin, NOT last-mile fiber. Im…
max_ttp_monthsinteger–Max time-to-power in months (ISO-level avg interconnection wait; HARD cut keeping projects in ISOs at/under this — PJM ~51, CAISO ~40, ISO-NE ~34, MISO ~34, ERCOT ~33, NYISO ~31, SPP ~24; <=30 leaves…
min_mwnumber–Minimum project capacity in MW, e.g. 1000 for 1 GW+
statusstring–Queue status filter. Default 'active' = still progressing (excludes withdrawn/cancelled/suspended/in-commercial-operation) — cross-ISO safe (SPP labels live projects 'IA FULLY EXECUTED/ON SCHEDULE' n…

No output schema declared.

No examples provided.

get_renewable_energy ~170

Get renewable energy data for a US state or location: renewable generation mix and resource inputs for PPA sizing.

NameTypeReqDescription
energy_typestring–Renewable type: "solar", "wind", or "combined"; omit for all
latnumber–Optional latitude in decimal degrees (-90 to 90) to find nearest projects within 50mi
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
lonnumber–Optional longitude in decimal degrees (-180 to 180) to find nearest projects within 50mi
longitudenumber–Alias for lon — either name works
statestring–US state abbreviation, e.g. TX, VA, AZ

No output schema declared.

No examples provided.

get_retirement_headroom ~249

Find scheduled generator retirements within a time horizon that could free grid capacity for a target MW, with the nearest substations to each.

NameTypeReqDescription
fuel_filterstring–Optional filter for retiring fuel categories, substring-matched (e.g., 'Coal', 'Natural Gas', 'Petroleum').
horizon_monthsintegeryesTime horizon in months to look ahead for planned retirements, 1-120 (e.g., 12, 18, 36).
limitinteger–Max results to return (1-500; default varies by tool)
region_isostring–Optional target region or ISO (e.g., 'MISO', 'PJM', 'ERCOT', 'SPP', 'CAISO', 'NYISO', 'ISONE'). Matches the generator's own EIA balancing-authority code — real market boundaries, not state lines. Com…
target_mwnumberyesMinimum required headroom in megawatts (MW) — filters to retiring generators at/above this size. Also passed through as the handoff's analyze_site capacity_mw (the DC you are siting).

No output schema declared.

No examples provided.

get_subsea_cables ~170

List subsea cable landing points near a coordinate, or the catalogue of tracked subsea cables.

NameTypeReqDescription
latnumber–Latitude of the site, e.g. 36.85 — with lon, returns landing points near it; omit both for the cable catalogue
latitudenumber–Alias for lat — either name works
limitinteger–Max results to return (1-500; default varies by tool)
lngnumber–Alias for lon — either name works
lonnumber–Longitude of the site, e.g. -75.98
longitudenumber–Alias for lon — either name works
radius_kmnumber–Search radius in km around lat/lon for landing points (default 200)

No output schema declared.

No examples provided.

get_tax_incentives ~58

List data-center tax incentive programs for a US state: sales-tax exemptions, property-tax abatements and other programs, with thresholds.

NameTypeReqDescription
statestring–US state abbreviation (required), e.g. VA, TX, AZ

No output schema declared.

No examples provided.

get_water_risk ~247

Get water-stress risk for a US lat/lon or state, for cooling-water planning.

NameTypeReqDescription
latnumber–Site latitude in decimal degrees (-90 to 90) for the most precise water-risk read, e.g. 33.45
latitudenumber–Alias for lat — either name works
lngnumber–Alias for lon — either name works
locationstring–Market NAME or metro slug instead of coordinates, e.g. "phoenix", "northern-virginia", "dallas". Resolved to that market's PUBLISHED CENTROID through the DCPI market row, and the answer carries a res…
lonnumber–Site longitude in decimal degrees (-180 to 180), e.g. -112.07
longitudenumber–Alias for lon — either name works
statestring–US state abbreviation as an alternative to lat/lon, e.g. AZ

No output schema declared.

No examples provided.

Install

How do I install the DC Hub — Data Center Site Selection & Colocation… MCP server?

DC Hub — Data Center Site Selection & Colocation… is a hosted endpoint at https://dchub.cloud/mcp/claude, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · dchub.cloud

# add to Claude Code
claude mcp add --transport http cloud-dchub-mcp-server 'https://dchub.cloud/mcp/claude'
Common questions

What is the DC Hub — Data Center Site Selection & Colocation… MCP server?

DC Hub — Data Center Site Selection & Colocation… is an MCP server listed in the public MCP registry as cloud.dchub/mcp-server. DCPI grid-power scores for 300+ markets, plus capacity to buy or lease; query and cite. This page covers its hosted endpoint (https://dchub.cloud/mcp/claude).

Is the DC Hub — Data Center Site Selection & Colocation… MCP server safe to use?

DC Hub — Data Center Site Selection & Colocation… scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the DC Hub — Data Center Site Selection & Colocation… MCP server expose?

DC Hub — Data Center Site Selection & Colocation… exposes 67 tools: search, fetch, execute_plan, search_facilities, get_facility, and 62 more. Their descriptions and schemas cost roughly 12,966 tokens of context every time the server is loaded.

Does the DC Hub — Data Center Site Selection & Colocation… MCP server require authentication?

No. We connected to DC Hub — Data Center Site Selection & Colocation… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the DC Hub — Data Center Site Selection & Colocation… MCP server still maintained?

DC Hub — Data Center Site Selection & Colocation… is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.