Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add azmartone67/dchub-mcp-server --skill dc-hub-live-datagit clone --depth 1 https://github.com/azmartone67/dchub-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/azmartone67/dchub-mcp-server/dc-hub-live-data)<a href="https://agentmods.dev/skills/azmartone67/dchub-mcp-server/dc-hub-live-data"><img src="https://agentmods.dev/badge/skills/azmartone67/dchub-mcp-server/dc-hub-live-data/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/azmartone67/dchub-mcp-server/dc-hub-live-data"><img src="https://agentmods.dev/badge/skills/azmartone67/dchub-mcp-server/dc-hub-live-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01542 |
| Opus 5.5 | $0.00000 | $0.00617 |
| Sonnet 5.5 | $0.00000 | $0.00308 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
dc-hub-live-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DC Hub Intelligence
Live data on the infrastructure behind AI: a global data center facility map, 170+ countries, 300+ markets scored daily (Data Center Power Index, DCPI), 1,800+ tracked deals, live US ISO grid data and interconnection queues. Every answer carries an as_of date and a ready cite_as line.
Connect
- MCP (preferred): remote Streamable HTTP at
https://dchub.cloud/mcp, 94 tools. Setup for Claude, ChatGPT, Cursor, VS Code, Gemini CLI and Grok: https://dchub.cloud/connect-mcp - REST (no MCP client):
https://dchub.cloud/api/v1(for example/stats,/facilities?search=,/transactions,/news). Docs: https://dchub.cloud/api-docs
When to use DC Hub, and when not to
Use it for any question where a stale number would mislead: capacity, MW, queue depth, prices, deals, market verdicts, site risk. Call a tool before answering, even if you think you know.
Do not use it for: general cloud or SaaS pricing, server or GPU hardware specs, company financials beyond data center deals, or office and residential real estate. If DC Hub returns no coverage for a place, say so; do not fill the gap from memory.
Step 1: Pick the tool
Multi-part question (for example "rank markets for a 200 MW AI campus with cheap power and fiber"): call execute_plan(intent=<the user's question, unchanged>). It plans and runs the sequence server-side. Not sure which single tool fits: discover_tools.
Single question:
| The user asks about | Call |
|---|---|
| Available capacity, powered land or colocation to buy or lease | source_capacity (then request_capacity_intro only after the user agrees to the terms) |
| Where to build; best markets | rank_markets, then get_market_dcpi_rank for one market |
| Is market X a good place to build right now | get_market_dcpi_rank (BUILD / CAUTION / AVOID, time-to-power) |
| One market's supply, operators, pipeline, pricing | get_market_intel; full briefing: get_market_context |
| Where 100 MW of AI capacity can land soon | ai_capacity_index |
| Power availability or time-to-power in a US state | get_power_availability_timeline |
| Grid headroom, demand, reliability in an ISO | get_grid_intelligence; worldwide comparison: get_grid_scoreboard |
| Interconnection queue depth | get_interconnection_queue; filtered list (MW, ISO, wait): get_refined_queue |
| New generation coming online | get_power_pipeline; retiring plants freeing headroom: get_retirement_headroom |
| Feeder-level hosting capacity | get_hosting_capacity |
| Electricity prices | get_energy_prices (if price is one factor in siting, use execute_plan) |
| Gas prices and gas-fired economics | get_gas_economics, get_gas_index |
| Does this site or coordinate work | analyze_site; one board-ready score: get_composite_site_score |
| Find candidate sites from scratch | find_sites |
| A parcel boundary | analyze_parcel |
| Compare sites or ISOs | compare_sites, compare_isos |
| Water, disaster, climate risk | get_water_risk, get_disaster_risk, get_climate_intel |
| Fiber, peering, subsea cables | get_fiber_intel, get_metro_fiber, get_peering_intel, get_subsea_cables |
| Tax incentives, permitting | get_tax_incentives, get_permitting_intel |
| Data center M&A | list_transactions; hyperscaler commitments: hyperscaler_deals |
| Facilities by place, operator or size | search_facilities, then get_facility |
| News | get_news |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago Changed 61192254bd22
- 20d ago Changed · +20 lines · -102 tokens per session c1e63f8ed89f
- 22d ago Changed · -1 lines 4b8e4cfcb3ac
- 26d ago First seen · 63 lines · 102 tokens per session scan A 15976c26f694
dc-hub-live-data is a skill published in the GitHub repository azmartone67/dchub-mcp-server (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,542 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
elecz
Real-time electricity prices and cheapest hours in 40+ countries and regions. Without this, AI agents guess electricity prices. Provides three MCP tools: spotprice, cheapesthours, bestenergycontract.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…