Skip to main content

FERC Open Data in AI Agents: Seller Authorizations, PPAs, and What the Catalog Actually Covers

· 5 min read
Tony Lewis
MCPBundles
Ask AI:
PerplexityClaudeChatGPTGoogleGrok

TL;DR​

  • The FERC Open Data MCP server exposes 28 datasets across 6 program assets on data.ferc.gov — including 4,435 market-based rate seller authorization rows and 44,563 entity-to-PPA links in the live catalog.
  • Ask for seller authorizations, PPA tables, company registration, or pending NEPA infrastructure projects and the agent discovers the dataset, reads metadata, and samples rows — no clicking through the portal asset tree.
  • Built for energy analysts, infrastructure researchers, and regulatory teams who need MBR and PPA context for power-market work — not a substitute for Electric Quarterly Reports or FERC Form 1 financials, which are not on this API yet.

If you work in power markets, you've probably lost twenty minutes in the open-data portal before — someone wants seller-authorization context or a sample of PPAs tied to entities, and you're still clicking assets wondering which table is current. The data is public. The friction is dataset IDs and knowing what the API won't filter for you.

The FERC Open Data integration on MCPBundles is for that catalog-navigation work from chat.

Don't pull rows until you know the dataset​

FERC's open-data surface is organized by program asset — Market-Based Rate Database, Company Registration, NEPA schedules, and others — each with nested datasets. Pulling rows before you know which dataset_id is current wastes calls paging the wrong table.

Keyword discovery comes first on a topic question. Ranked matches come back with IDs, parent asset names, and descriptions — one query instead of walking the portal tree.

For orientation, ask what's in the catalog at all. You get asset count, dataset count, a compact list, and an honest note that EQR and Form 1 sit outside this API.

MBR authorizations and PPAs​

Market-based rate research usually lands on two tables.

Dataset 9 — MBR Authorizations in the current catalog — holds about 4,435 seller authorization rows: reporting entity, parent company, docket, effective dates, and related fields. After discovery, sample a few rows and read the column dictionary before you trust field names in a brief.

Dataset 17 — Entities to PPAs — is larger: 44,563 rows linking entities to power purchase agreements. Same discipline: metadata, dictionary, then a small page read.

Everything is paginated. There is no server-side "only solar" or "only PJM" filter. When a question implies a regional or balancing-authority slice, the honest answer is what the catalog contains and what it cannot filter — not a silent full-table scan pretending to be geography.

Named companies yes; geography no​

When someone names a counterparty, row search works. Summit Grid parent's market-based rate seller authorization can resolve to a docket after you've found the MBR dataset — the same path you'd use for any named utility in authorization data.

Row search is not a geographic query engine. Active solar PPAs in PJM sounds reasonable in conversation, but the API doesn't expose a balancing-authority column you can filter server-side. You discover the PPA dataset, explain the limitation, and you don't page through forty-four thousand rows hunting for a column that isn't there.

Worth saying up front in datacenter or interconnection briefs: this connector is catalog navigation plus deliberate sampling, not a replacement for EQR contract exports.

NEPA and registration are different drawers​

Infrastructure diligence often needs the NEPA schedule — about 233 rows in the current NEPA Schedule dataset, with project names, statuses, and dates. Pending infrastructure projects show up as real project names once you've found that dataset and read a page.

Company registration is a separate asset. A FERC company identifier for a named parent routes through registration datasets, not MBR authorizations. Registration IDs and seller-authorization dockets answer different questions — keep the drawers separate.

EQR and Form 1: say no early​

The expensive mistake is substituting the wrong table when someone asks for Electric Quarterly Reports or FERC Form 1 utility financials. Neither is published on data.ferc.gov today.

I've seen chat answers built from unrelated annual-charge rows when the user asked for utility financials. Don't do that. Say the gap out loud and point to what is available — MBR authorizations and entity-to-PPA links for market-based-rate context.

Enable and ask​

Turn on the FERC Open Data server in your workspace — no separate FERC sign-in on your side — and ask from Claude, Cursor, ChatGPT, or wherever you already run research. Start with what's in the catalog, then find market-based rate seller authorization datasets and sample three rows. One pass proves coverage and field names.