Skip to main content
Glama

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

by cloud.dchub

AI Capacity Index

ai_capacity_index
Read-onlyIdempotent

AI Compute Capacity Index — ranks data center markets by where 100MW of AI training capacity can land in the next 30/60/90 days. Returns top markets with facility_count, operator_count, deployable_mw estimate (megawatts), hyperscale_ready flag, rack power density and cooling-type signals where facility data carries them, and composite score (depth + diversity + power). Refreshed Fridays 14:00 UTC. Use for AI capex planning, GPU cluster siting, hyperscaler deal forecasting. Do NOT use for a general best-markets ranking (use rank_markets) or forward grid-emergence (use grid_transition_radar).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNumber of top markets to return (default 20)
horizonNoDeployment horizon in days: 30, 60, or 90 (default 90)

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

A4.5/5.0
Behavior4/5

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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, and the description adds useful behavioral context beyond those: the refresh cadence ('Refreshed Fridays 14:00 UTC'), the ranking logic ('composite score (depth + diversity + power)'), and the caveat that cooling-type signals appear only 'where facility data carries them.' This meaningfully supplements the annotation metadata.

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

Conciseness5/5

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

The description is three sentences with no wasted words. It front-loads the core ranking behavior, then lists what is returned, then covers usage boundaries. Every sentence contributes either to selection, invocation, or differentiation.

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 the tool has an output schema, the description does not need to enumerate return types exhaustively, but it still summarizes the key output fields and scoring rationale. It also provides refresh timing, use cases, and explicit sibling exclusions, making it fully self-sufficient for correct tool selection and invocation.

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% for both parameters, so the baseline is 3. The description reinforces the horizon concept ('next 30/60/90 days') and adds business context for why the parameter matters, but it does not provide additional parameter-level syntax or format details beyond what the schema already documents.

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 opens with a specific verb and resource: 'ranks data center markets by where 100MW of AI training capacity can land in the next 30/60/90 days.' It clearly separates this from sibling tools by naming rank_markets and grid_transition_radar as alternatives, so an agent can identify the correct tool without inspecting its schema.

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?

The description explicitly states recommended use cases ('AI capex planning, GPU cluster siting, hyperscaler deal forecasting') and gives direct exclusion guidance: 'Do NOT use for a general best-markets ranking (use rank_markets) or forward grid-emergence (use grid_transition_radar).' This gives the agent both positive and negative selection criteria.

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