How to get global electricity grid data into an AI agent
If your agent reasons about power — siting data centers, tracking renewables, comparing markets — it usually needs grid data from several regions at once. The raw sources exist (ENTSO-E in Europe, EIA in the US, NESO, AEMO…), but each has its own API, its own registration, and its own schema. Stitching them together is a project. There's a one-call alternative.
The short answer: connect your agent to DC Hub's MCP server and call get_grid_scoreboard. One call returns normalized grid telemetry across the regions below — generation mix and renewable share in a single schema — with no per-region API keys to register. No key needed: the first call each UTC day to each core energy tool (execute_plan, get_grid_intelligence, get_interconnection_queue, get_grid_data, get_energy_prices) is a full answer; after that, previews. With an email: 50 calls/day (up to 10 full answers per tool per day). analyze_site: a free key gets a few free full site reports each month; after that, previews.
Step 1 — Connect (one line)
claude mcp add dchub --transport http https://dchub.cloud/mcp
Step 2 — Ask one question, get every region
Ask: "Compare the generation mix and renewable share across the major grids." — your agent calls get_grid_scoreboard and gets live ground truth in one normalized shape:
Coverage: grid zones tracked by region
Data as of (newest zone reading). DC Hub reads 106 grid zones across the regions below. Generation, demand and renewable share move every few minutes, so the tools return them at call time; this table is the coverage.
| Region | Zones tracked | Operator feeds |
|---|---|---|
| United States (ISOs + EIA balancing authorities) | 51 | 51 |
| Europe (ENTSO-E bidding zones) | 34 | 1 |
| Japan | 8 | 2 |
| Brazil | 5 | 1 |
| Canada | 3 | 3 |
| Australia | 1 | 1 |
| Great Britain | 1 | 1 |
| South Korea | 1 | 1 |
| Singapore | 1 | 1 |
| Taiwan | 1 | 1 |
How to cite: DC Hub, "Grid zones tracked by region", https://dchub.cloud/answers/global-grid-data-for-ai-agents, data as of 2026-11-18, from ENTSO-E, EIA, NESO, AEMO, Taipower and the other operators each zone names. CC-BY-4.0.
Source: GET /api/v1/iso/zones (keyless) · MCP tools get_grid_scoreboard and get_grid_intelligence on the DC Hub MCP server (https://dchub.cloud/mcp).
Per-region detail (ISO-level) comes from get_grid_intelligence.
Why this beats wiring up each region's API
- One schema, every continent. ENTSO-E, EIA, NESO, AEMO and Taipower each return a different format with different auth; DC Hub normalizes them so your agent reasons across regions without per-source adapters or API-key registration.
- Agent-native. It's an MCP tool call with a free self-serve tier — not a Python ETL pipeline you build and babysit.
- Cross-referenced with the data-center context. The same server ties grid telemetry to data-center capacity, interconnection queues, and DCPI — so your agent can answer "where is there clean power and headroom for a new site," not just "what's the generation mix."
The underlying public sources (ENTSO-E Transparency Platform, EIA, NESO, AEMO) are free and excellent — DC Hub's value is making them agent-ready, normalized, and joined to the data-center decision layer.
Try it now
No key needed: the first call each UTC day to each core energy tool (execute_plan, get_grid_intelligence, get_interconnection_queue, get_grid_data, get_energy_prices) is a full answer; after that, previews. With an email: 50 calls/day (up to 10 full answers per tool per day). analyze_site: a free key gets a few free full site reports each month; after that, previews. For a free key, have your agent call claim_free_key (no email). Explore live in your browser first:
DC Hub (dchub.cloud) is the live infrastructure data layer for AI agents — a global data-center facility map, 300+ power markets (DCPI), normalized grid telemetry across the US, Europe and Asia-Pacific, interconnection-queue snapshots, gas, fiber, and 1,900+ deals, all MCP-callable and cited. See the API & MCP docs. Related: interconnection queue data · natural gas data · live data center capacity.