Skip to main content
Glama

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

by cloud.dchub

Site Selection Canvas

site_selection_canvas
Read-onlyIdempotent

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 DC Hub 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
isoNoISO/RTO code, e.g. ERCOT or PJM — alias for `region`. Use either; `region` wins if both are sent.
limitNoNumber of shortlist markets to return
stateNoUS state code, e.g. OH — alias for `region`. Use either; `region` wins if both are sent.
regionNoGeography scope: a US state code like TX, an ISO like ERCOT, or a region like us/apac. `state` and `iso` are accepted as aliases for this same filter.
mpp_payNoAutonomous payment (Stripe MPP), step 1: set true to receive a signed $0.50 payment challenge for this call instead of the free preview. No money moves — a challenge is a price quote. Humans never set this, so it does not affect the normal free/trial funnel.
verdictNoOptional DCPI verdict filter: BUILD, CAUTION, or AVOID — or ALL to see every scored market in the geography. Defaults to BUILD,CAUTION, so a geography whose markets are all AVOID returns matched:0 plus an `empty_result` block explaining that; re-run with verdict=ALL to see those rows.
max_monthsNoMaximum acceptable time-to-power in months, 1-120, e.g. 24
capacity_mwNoTarget power load for the build in megawatts (MW), 1-5000, e.g. 100
mpp_credentialNoAutonomous payment (Stripe MPP), step 2: the Shared Payment Token you minted for challenges[0]. Set it here to pay $0.50 for this single call and receive the full result — no API key, no subscription, no human. One payment covers one call.

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. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: it reveals a free-preview versus paid-key tier ('with a paid key, the synthesis decision layer') and frames the call as a single find->rank->shortlist->verdict flow, which sets accurate expectations about scope.

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

Conciseness4/5

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

The description is front-loaded with the core purpose and includes a concrete example plus use-case exclusions. It is slightly repetitive with 'end-to-end', 'find->rank->shortlist->verdict', and 'this runs the full find to rank to shortlist to verdict flow', but each sentence still earns its place.

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

Completeness4/5

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

For a tool with 9 parameters, an output schema, and rich annotations, the description covers the main invocation pattern, the paid-tier behavior, and key exclusions. It does not need to explain return values because an output schema exists. Minor gaps like the default verdict filter are handled by the schema, so the description is sufficiently complete for an agent to call it correctly.

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%, so the schema already documents all nine parameters, including aliases and the MPP payment flow. The description adds an example (capacity_mw=100 region=TX max_months=24) and high-level mappings like 'capacity target + geography + deadline', but does not add meaning beyond what the schema already provides. Baseline 3 is appropriate.

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?

The description names a specific verb and resource: 'Guided end-to-end data-center site selection' over the 'DC Hub Power Index', returning a ranked shortlist and decision layer. It clearly differentiates from siblings by naming analyze_site and get_dchub_recommendation as alternatives for different scenarios.

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?

Explicit when-to-use criteria are stated: 'Give a capacity target + geography + deadline and get a ranked shortlist'. It also gives a worked example (capacity_mw=100 region=TX max_months=24) and explicit exclusions with named alternatives: 'Do NOT use for a single known parcel (use analyze_site) or an open-ended where-should-I-build question (use get_dchub_recommendation)'.

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

All DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, Fiber toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation1/5

With 85 tools, several families are heavily overlapping: semantic_search and search_intelligence are explicitly documented as the same retrieval with different call shapes, save_site and save_to_shortlist both persist sites, and list_saved_sites and get_shortlist both read saved sites. Additionally, site scoring is split across analyze_site, get_composite_site_score, score_facility, and rank_sites, making correct tool selection very difficult for an agent.

Naming Consistency3/5

All names are snake_case and mostly readable, but conventions are mixed: many use get_* (get_facility, get_grid_intelligence), others use verb phrases (analyze_site, compare_isos, rank_markets), and some are bare noun phrases (ai_capacity_index, hyperscaler_deals, grid_transition_radar, site_selection_canvas). The search family alone uses search, search_facilities, semantic_search, and search_intelligence with no consistent pattern.

Tool Count1/5

85 tools is an extreme count for any MCP server, far beyond the 3-15 well-scoped range and above the 50+ threshold described as an extreme mismatch. Even with a wide domain like data-center siting, this many tools overwhelms agent context and makes selection costly.

Completeness4/5

The domain surface is exceptionally broad: siting, grid, gas, fiber, water, climate, tax, permitting, deals, news, facilities, saved shortlists, alerts, webhooks, key management, and research dossiers are all covered with connected workflows. Minor gaps exist, such as no delete or update for saved sites and no pause/resume for standing intents, but these are workable rather than blocking.

Resources