Skip to main content
Glama
azmartone67

DC Hub Intelligence

Source Capacity

source_capacity
Read-onlyIdempotent

Search data-center capacity to buy or lease by size in kW or MW and location, and match a whole requirement to single listings or bundles.

Instructions

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. Returns listing cards (market, region, capacity — with contiguous_kw and min_contract_kw wherever a listing declares them — status and when each listing was last updated) to any caller, plus the filters applied and the program status (live, or upcoming while the first listings are onboarded). Pass slug for one listing: a signed-in human who has accepted the introduction terms sees its specs (signed in means a key with an email bound via claim_free_key then bind_email, or an OAuth connection; accept_capacity_terms records the acceptance the first time); others get the card and the unlock steps. The provider's identity, site and contact are released only after the provider accepts a deal registration, which request_capacity_intro submits, and the listing's disclosure block says whether they have been. To match a whole requirement instead, pass target_mw or target_kw (optionally min_chunk_kw, max_sites, max_providers, available_by): returns exact single-listing fits, multi-site or multi-provider bundles and, when nothing fits, a shortfall timeline; matching needs a signed-in human, and providers stay anonymised until an introduction is accepted. Do NOT use for the public facility directory (use search_facilities) or for completed M&A (use list_transactions).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugNoOne listing: its slug or numeric id exactly as items[].slug / items[].id return it. Omit to browse teaser cards
limitNoMax results to return (1-500; default varies by tool)
stateNoBrowse filter: two-letter US state, e.g. "TX"
marketNoBrowse filter: market name as it appears on a listing, e.g. "Dallas"
min_kwNoBrowse filter: the size your human needs, in kW (min_mw is the same filter in MW). Matched against what a listing can ACTUALLY deliver, not just 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 listing answers only when this size fits the block it declares — a site with a big total but a small contiguous block is not a hit, and a big site willing to contract small chunks is. A listing that declares neither is matched on its total.
min_mwNoBrowse filter: the size your human needs, in MW (min_kw is the same filter in kW). Matched against what a listing can ACTUALLY deliver, not just 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 listing answers only when this size fits the block it declares — a site with a big total but a small contiguous block is not a hit, and a big site willing to contract small chunks is. A listing that declares neither is matched on its total.
regionNoBrowse filter: comma-separated regions from north_america, latin_america, europe, asia_pacific and middle_east_africa; the aliases emea, apac, latam and americas also work, e.g. "europe" or "emea, apac"
locationNoBrowse filter: comma-separated free text matched against each listing's region, country, state and metro, e.g. "Germany" or "Texas, Phoenix"
max_sitesNoMatch mode: how many listings the requirement may be split across. Default one, which allows exact fits only; raise it to allow bundles
target_kwNoMatch mode: the whole requirement, in kW (target_mw is the same in MW; give one)
target_mwNoMatch mode: the whole requirement, in MW (target_kw is the same in kW; give one). Returns exact fits, bundles and a shortfall instead of teaser cards. Needs a signed-in human
available_byNoBrowse filter: only listings available by this date, as YYYY-MM or YYYY-MM-DD. With a target it is the date the whole requirement must be deliverable by
min_chunk_kwNoMatch mode: the smallest piece, in kW, your human will contract at any one listing. Default: no minimum
delivery_typeNoBrowse filter: how the capacity is delivered: land, powered_shell, turnkey or colocation
max_providersNoMatch mode: how many different providers a bundle may use. Default: the same as max_sites

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
quotaNoCaller quota state (remaining calls, tier) when available.
_entityNoPayload class discriminator (e.g. facility|market|iso_grid|queue_results|deal|report|response) — branch on this before parsing the rest.
citationNoMachine-readable citation: how to attribute DC Hub (dchub.cloud) for this payload. Normally an OBJECT {source, url, license, cite_as, retrieved_at}; a bare string is accepted and carries the attribution line itself.
provenanceNoCollection-level provenance block: {source, method, as_of, verification_counts, cite_url_template, license, cite_as}. Quote the verification level when citing.
_front_doorNoIn-band front-door hint (first workflow-entry tool of a session): call plan_query(intent) first for the ordered multi-step plan.
_return_loopNoSuggested next-session delta call (get_changes since=24h) so you pull only what changed.
site_evaluation_handoffNoPre-built follow-up calls (analyze_site / get_water_risk args) when the payload carries coordinates — an array of {tool, parameters, why} entries.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.12.21
    • changedInput schema / properties / available_by / description
      Previous value: -"Browse filter: only listings available by this date, as YYYY-MM or YYYY-MM-DD"New value: +"Browse filter: only listings available by this date, as YYYY-MM or YYYY-MM-DD. With a target it is the date the whole requirement must be deliverable by"
    • addedInput schema / properties / max_providers
      Added value: +{
      +  "description": "Match mode: how many different providers a bundle may use. Default: the same as max_sites",
      +  "maximum": 6,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / max_sites
      Added value: +{
      +  "description": "Match mode: how many listings the requirement may be split across. Default one, which allows exact fits only; raise it to allow bundles",
      +  "maximum": 6,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / min_chunk_kw
      Added value: +{
      +  "description": "Match mode: the smallest piece, in kW, your human will contract at any one listing. Default: no minimum",
      +  "type": "number"
      +}
    • addedInput schema / properties / target_kw
      Added value: +{
      +  "description": "Match mode: the whole requirement, in kW (target_mw is the same in MW; give one)",
      +  "type": "number"
      +}
    • addedInput schema / properties / target_mw
      Added value: +{
      +  "description": "Match mode: the whole requirement, in MW (target_kw is the same in kW; give one). Returns exact fits, bundles and a shortfall instead of teaser cards. Needs a signed-in human",
      +  "type": "number"
      +}
  2. Changed2 schema fields changedv2.12.15
    • changedInput schema / properties / min_kw / description
      Previous value: -"Browse filter: only listings with at least this much capacity, in kW (min_mw is the same filter in MW)"New value: +"Browse filter: the size your human needs, in kW (min_mw is the same filter in MW). Matched against what a listing can ACTUALLY deliver, not just 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 listing answers only when this size fits the block it declares — a site with a big total but a small contiguous block is not a hit, and a big site willing to contract small chunks is. A listing that declares neither is matched on its total."
    • changedInput schema / properties / min_mw / description
      Previous value: -"Browse filter: only listings with at least this much capacity, in MW"New value: +"Browse filter: the size your human needs, in MW (min_kw is the same filter in kW). Matched against what a listing can ACTUALLY deliver, not just 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 listing answers only when this size fits the block it declares — a site with a big total but a small contiguous block is not a hit, and a big site willing to contract small chunks is. A listing that declares neither is matched on its total."
  3. Changed5 schema fields changedv2.12.14
    • addedInput schema / properties / available_by
      Added value: +{
      +  "description": "Browse filter: only listings available by this date, as YYYY-MM or YYYY-MM-DD",
      +  "type": "string"
      +}
    • addedInput schema / properties / delivery_type
      Added value: +{
      +  "description": "Browse filter: how the capacity is delivered: land, powered_shell, turnkey or colocation",
      +  "enum": [
      +    "land",
      +    "powered_shell",
      +    "turnkey",
      +    "colocation"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / location
      Added value: +{
      +  "description": "Browse filter: comma-separated free text matched against each listing's region, country, state and metro, e.g. \"Germany\" or \"Texas, Phoenix\"",
      +  "type": "string"
      +}
    • addedInput schema / properties / min_kw
      Added value: +{
      +  "description": "Browse filter: only listings with at least this much capacity, in kW (min_mw is the same filter in MW)",
      +  "type": "number"
      +}
    • addedInput schema / properties / region
      Added value: +{
      +  "description": "Browse filter: comma-separated regions from north_america, latin_america, europe, asia_pacific and middle_east_africa; the aliases emea, apac, latam and americas also work, e.g. \"europe\" or \"emea, apac\"",
      +  "type": "string"
      +}
  4. Addedv2.12.13

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), yet the description adds substantial context: how size is matched against contiguous_kw/min_contract_kw rather than headline totals, the auth prerequisites for match mode and slug details (claim_free_key then bind_email, accept_capacity_terms), and the disclosure rule that provider identity is released only after an accepted deal registration.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger, but the body is a dense wall of run-on clauses mixing matching semantics, auth, disclosure and mode switching with little structural separation. Every fact is relevant, but it is hard to scan for an agent under time pressure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 15 parameters, an output schema, and rich annotations, the description covers what the agent still needs: mode selection, auth gating, disclosure state, and how results differ per caller. Nothing essential to correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the description largely restates the same min_kw/min_mw matching rule already present in the schema. It does add value by framing the browse-vs-match mode split and the slug behavior, but most parameter detail is duplicated, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: search DC Hub Capacity Source for data-center capacity by size and/or location. It explicitly names the siblings it is not (search_facilities for the public directory, list_transactions for completed M&A), so an agent can distinguish it without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger ('Use when your human needs data-center CAPACITY to buy or lease') and closes with explicit exclusions routed to named alternatives. It also clarifies the two operating modes (browse filters vs. target_* requirement matching), which is the key routing decision.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools