splitbasket-prices

Cached US grocery prices for developers and agents, from the SplitBasket weekly price panel.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Search Products: Find grocery products matching a text query near a location, with the price each nearby store last showed. Use this first: it returns the `banner` + `product_id` pairs that `get_price
  • Get Price: The cached price of one exact product (banner + product_id) at one location. Answers at the most local tier that has data and reports it in `match_level`. For target, smartandfinal, bashas,
  • Compare Price: For one query, the best-matching product at EACH banner near a location, so you can compare. Compare on `unit_price` (canonical $/oz, $/fl_oz or $/each), not `price` — the best match at

What data it sees

Do you need an account

An API key from the service settings is required

Cached US grocery prices for developers and agents, from the SplitBasket weekly price panel. Search products, look up an exact price, and compare across banners (Walmart, Costco, Whole Foods, Sprouts, Sam's Club, Aldi and more). Every price carries its observation date, and a coverage tool reports what the API can answer at a location before you build on it — returning no_data rather than a plausible wrong number. Free keys during closed beta: email team@splitbasket.shop.

How to connect

How to connect splitbasket-prices to Claude

The server address to paste into Claude settings:

https://splitbasket-prices--ana-bujosa.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect splitbasket-prices to ChatGPT

The server address to paste into ChatGPT settings:

https://splitbasket-prices--ana-bujosa.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect splitbasket-prices to Cursor

The server address to paste into Cursor settings:

https://splitbasket-prices--ana-bujosa.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

search_productsFind grocery products matching a text query near a location, with the price each nearby store last showed. Use this first: it returns the `banner` + `product_id` pairs that `get_price` and `live_check` take. Prices are CACHED, not live — every result carries `price_as_of` and a `match_level` saying how far it generalized (exact_store, banner_metro, banner_state).
get_priceThe cached price of one exact product (banner + product_id) at one location. Answers at the most local tier that has data and reports it in `match_level`. For target, smartandfinal, bashas, frys and foodsco this will NOT fall back to a state-level answer — their prices measurably do not hold across metros — and returns found:false instead of a plausible wrong number.
compare_priceFor one query, the best-matching product at EACH banner near a location, so you can compare. Compare on `unit_price` (canonical $/oz, $/fl_oz or $/each), not `price` — the best match at two banners is often two different pack sizes. Matching is deterministic string matching, so check the returned `name` and `size_text` before trusting a comparison. TO ESTIMATE A BASKET, call this once per item and sum it yourself: this API sells per-item prices, not a shopping plan.
coverageWhat this API can actually answer at a location, before you ask it: which banners have cached prices in range right now, how old the freshest one is, which will refuse to generalize past metro, and each banner's nearest store_id. `comparison_depth` under 2 means there is nothing to compare there. Reports MEASURED coverage, not collection plans. Call this before a series of compare_price calls in an unfamiliar area.
live_checkFetch prices from the retailer RIGHT NOW for up to 20 search terms at one store, when a cached price is too old for your purpose. Returns a job id and an ETA measured in minutes, not a price — poll with the `live_check_status` tool. Paid tier only. When it completes, the prices are also readable through get_price at match_level exact_store.
live_check_statusPoll a live_check job. Terminal statuses: done, failed, rejected.