Store Price Tracker in ChatGPT
Track an online store's prices. The MCP server is https://stores.openkrill.app/mcp. No key. The steps below are only for ChatGPT. A call to check_store_prices was checked against that server on 2026-10-01.
What this server answers
Ask what an online store sells, what it charges and what changed since the last time anyone looked.
Ask "track competitor prices on allbirds.com", "what did gymshark.com change this week?", "which products on this store are sold out?" or "how has the price of this hoodie moved?".
Store Price Tracker reads the public product feed that Shopify stores publish at /products.json, the same list any visitor's browser can fetch without logging in.
It reports products, prices, variants and availability, and compares each daily snapshot with the one before it: new products, removed products, price changes and stock changes, per variant.
A store you ask about is added to a daily snapshot list, so its price history grows over time and can be read back for any product.
It checks the store's robots.txt first, identifies itself with a clear User-Agent, pauses between requests and backs off when a store asks for fewer.
Stores that are not on Shopify, or that keep their feed private, are reported as unavailable.
It stores only public product data (titles, prices, variants, availability) and the store's address.
Nothing about you is kept: no prompts, no account and no IP address, only a daily count of calls per tool.
What it can do
- Lists the products, prices, variants and availability of a Shopify store
- Shows new products, removed products, price changes and stock changes since the previous daily snapshot
- Keeps a daily snapshot of every store it is asked about, so price history builds up
- Reads the price and availability history of one product
- Compares up to five stores in one answer
Tools
check_store_prices, Check a store's products and price changes. Read an online store's products, prices and availability, and what changed since its previous daily snapshot. Use it for questions like "track competitor prices on allbirds.com", "what did gymshark.com change?", "did this store drop prices?", "what is new or sold out at this store?". Pass store web addresses, up to 5. Works for stores on Shopify that publish their public product feed (/products.json). The store is added to a daily snapshot list, so its history builds up. Optional filters: query (text in a product's title, brand or type), limit. Returns per store the snapshot date, product count, currency, counts and lists of new products, removed products, price changes and availability changes per variant, and matching products with price, variants and availability. The first snapshot of a store has no changes to compare with.get_product_price_history, Get a product's price history. Read how one product's price and availability moved over the days a store has been tracked. Use it for questions like "how has the price of this hoodie changed?", "when did this product go on sale?", "has this been out of stock?". Pass the store's web address and the product's link, handle or title (or part of it). Returns per variant the price, the compare-at (was) price and availability on each day something changed, from the first snapshot to now. History starts when the store was first tracked; a store never asked about before has a single snapshot. Several matching products come back as a list of titles to choose from.
Add Store Price Tracker in ChatGPT
ChatGPT does not read a local config file. A custom MCP server is added in the product, and only after developer mode is on. These steps were checked against OpenAI's plugin connect guide and the ChatGPT MCP guide on 2026-10-01. Developer mode can be hidden by a workspace policy, so a Team or Enterprise admin may have to allow it first.
- Open ChatGPT settings, then Security and login, and turn on Developer mode.
- Open ChatGPT plugins and select the plus button.
- Enter a name such as "Store Price Tracker" and a one-line description of what you want it to answer.
- Under Connection, choose the public endpoint and paste
https://stores.openkrill.app/mcp. Include the/mcppath. Do not add a tunnel id: this server is already public. - Create the connection and review the tools ChatGPT lists. You should see
check_store_prices,get_product_price_history. The feedback tools on the same server are optional and not required for the lookup. - Start a new conversation, add the connection from the tools menu, and ask: Track competitor prices on allbirds.com
No API key and no OAuth client id are required. The server answers without a login. Calls are limited per network and per day, and a limit comes back as a tool error rather than a partial answer. If the tool list is stale after a server change, open the connection and select Refresh, then start a new conversation.
The ChatGPT desktop app, Codex CLI and IDE extension share a different config. In the desktop app, open Settings, then MCP servers, choose Add server, select Streamable HTTP, and paste the same URL. In ~/.codex/config.toml the equivalent is a table named mcp_servers.store-prices with url = "https://stores.openkrill.app/mcp". ChatGPT on the web does not read that file. A published directory listing is also a different path: this page is the developer-mode connection, not a claim that Store Price Tracker is already in the ChatGPT directory.
Treat the server as untrusted until you have read a few answers. A remote MCP server sees the arguments the model sends. Store Price Tracker is read-only and documents what it sends onward on the privacy page.
A call checked on 2026-10-01
allbirds.com is a public Shopify store used in the plugin's own starter prompts. The request below was posted to https://stores.openkrill.app/mcp as tools/call. HTTP 200. Source: the Store Price Tracker server, read 2026-10-01.
{
"method": "tools/call",
"params": {
"name": "check_store_prices",
"arguments": {
"stores": [
"allbirds.com"
],
"limit": 2
}
}
}- stores. 1 returned
- stores status. ok
Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.