About Heating Oil and Propane Prices MCP
Heating Oil and Propane Prices MCP provides EIA residential fuel price data for AI assistants and people comparing household heating costs. It combines current weekly averages, historical prices and delivery-cost estimates, while identifying areas the survey does not cover.
Key features
- 01Current state and regional prices
- 02Weekly price changes and history
- 03Delivery and fuel-cost estimates
- 04Survey coverage and release dates
Use cases
- 01Check this week’s state fuel price
- 02Compare prices with a year ago
- 03Estimate a 200-gallon delivery
- 04Compare oil and propane per Btu
MCP support
This MCP server exposes tools for current heating oil and propane prices, price history and cost estimates. It reads EIA survey data at call time and requires no API key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcpclaude mcp add --transport http theluckystrike-heating-oil-propane-prices https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp{"mcpServers":{"theluckystrike-heating-oil-propane-prices":{"type":"http","url":"https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp"}}}Open in Cursor{"servers":{"theluckystrike-heating-oil-propane-prices":{"type":"http","url":"https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"theluckystrike-heating-oil-propane-prices":{"type":"http","url":"https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp"}}}{"mcpServers":{"theluckystrike-heating-oil-propane-prices":{"serverUrl":"https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEheating-oil-propane-prices-mcp
Heating oil and propane prices for AI assistants. Ask for this week's price per gallon in your state and get the U.S. Energy Information Administration (EIA) average, the change from last week and a year ago, and what a tank fill costs.
This is a Model Context Protocol (MCP) server. It reads the EIA weekly residential heating oil and propane survey at call time. It needs no API key.
Tools
| Tool | What it returns |
|---|---|
get_heating_oil_propane_prices | This week's EIA average residential heating oil and propane price per gallon (taxes included) for the US, an EIA region or a surveyed state, the change from last week, the last five survey weeks, the price a year ago and the next release date. |
get_heating_fuel_price_history | Weekly prices for a fuel and area between two dates (most series start in 1990), with high, low and average. |
estimate_heating_fuel_cost | Cost of a delivery at this week's state average (or your price), cost per million Btu, and heating oil vs propane per million Btu, optionally against your electricity or natural gas rate. |
Every result has structured JSON, a one-paragraph summary, as_of, source and more (a page on mcpstamp.com).
What it knows that your model does not
- This week's price. EIA publishes new prices every Wednesday from October to March, so a remembered number is stale.
- Which states EIA surveys. Heating oil covers 21 Northeast and Midwest states; propane covers 38. Other states get the covered list, not a made-up number.
- Real year-over-year change from the EIA history file.
Install
Hosted (Claude.ai custom connector, ChatGPT developer mode)
Paste this URL. No token, no sign-up. It works now.
https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp
Claude Code
claude mcp add --transport http heating-fuel-prices https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp
Claude Desktop
Claude Desktop adds remote servers under Settings, Connectors, Add custom connector. Paste the URL above.
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"heating-fuel-prices": { "url": "https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp" }
}
}
VS Code
Add to .vscode/mcp.json:
{
"servers": {
"heating-fuel-prices": { "type": "http", "url": "https://heating-oil-propane-prices-mcp.lipmichal.workers.dev/mcp" }
}
}
Local stdio (after npm release)
The npm package is not published yet. After it is, run it locally with Node 20 or newer:
claude mcp add heating-fuel-prices -- npx -y heating-oil-propane-prices-mcp
Example prompts
- "What are heating oil prices this week?"
- "How much is propane in Maine right now, and how does it compare with last year?"
- "What will 200 gallons of heating oil cost me in Connecticut?"
- "Is propane or heating oil cheaper per Btu in Pennsylvania?"
- "Show me propane prices in Minnesota over the last year."
Data sources
Full list with fetch dates in DATA_SOURCES.md.
- EIA weekly residential heating oil prices and propane prices, read at call time.
- EIA weekly history pages (LeafHandler) for year-ago and history.
- EIA heat content: heating oil 138,500 Btu per gallon, propane 91,452 Btu per gallon.
Limitations
- State averages from a dealer survey, not a quote. Dealer price, delivery fees, volume and contracts vary.
- From April to September EIA collects one price a month.
- Not every state is surveyed (no heating oil price for Texas, for example).
- The hosted server caches EIA pages for up to an hour.
More
More MCP servers that answer questions your assistant cannot answer alone are on mcpstamp.com.
Part of the Zovo MCP collection: https://mcp.zovo.one
Built by theluckystrike.
Development
npm install
npm test # builds, then runs the fixture tests and an offline stdio test
node scripts/stdio-transcript.mjs # live stdio round trip, writes .live/stdio-transcript.jsonl
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.