
Connects Claude to the US Energy Information Administration's v2 API for querying official energy data. Part of the Pipeworx gateway ecosystem, which means you can either use this standalone EIA endpoint or connect to their full gateway for access to 600+ data sources. The interesting bit is the ask_pipeworx function that handles natural language queries instead of making you construct API calls manually. Useful when you need current energy statistics, production data, consumption trends, or price information from the official US government source. Runs over streamable HTTP, so no local installation required.
The official US energy data: petroleum, natural gas, electricity, coal, renewables, nuclear, total energy, international energy. Production, consumption, prices, reserves, imports/exports — at national, state, and (for electricity) plant level. Free, requires a free API key.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
For energy questions — "what's the price of natural gas?", "how much electricity comes from solar?", "are gasoline prices rising?" — EIA is the source. Government-grade data, no commercial markup. Pair with FRED for energy-related macro indicators and NOAA for energy-relevant weather context.
Common flows:
EIA Open Data API requires a free key from https://www.eia.gov/opendata/register.php. Pass via _apiKey. Generous rate limits.
| Dataset | Cadence | Use |
|---|---|---|
| Petroleum & Other Liquids | Weekly / monthly | Crude oil prices, gasoline, distillates, OPEC |
| Natural Gas | Weekly storage, monthly production | Pricing, storage, consumption |
| Electricity | Monthly | Generation by fuel, retail rates by state |
| Coal | Monthly / annual | Mining, prices, exports |
| Renewable & Alternative Fuels | Monthly | Solar, wind, biofuels, electric vehicle charging |
| Total Energy / Annual Energy Outlook | Annual | Long-term forecasts |
EIA series follow dataset_id.frequency.region.product patterns. Examples:
PET.RWTC.D — WTI crude, dailyNG.RNGC1.D — Natural gas Henry Hub, dailyELEC.GEN.SUN-CA-99.M — California solar generation, monthlyPET.EMM_EPMR_PTE_NUS_DPG.W — US weekly average regular gasoline priceUse the eia_search tool to find IDs rather than constructing them manually.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"eia": {
"url": "https://gateway.pipeworx.io/eia/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/eia/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Eia data" })
The gateway picks the right tool and fills the arguments automatically.
MIT