---
name: store-prices-jobs
description: "Step-by-step job recipes for the Store Price Tracker MCP server: Check a store's products and price changes; Compare prices and find gaps across stores; Get a product's price history. Use when the user asks things like \"Track competitor prices on allbirds.com.\" or \"Compare product prices on mysneakerstore.com with allbirds.com and find products with at least 15% price gap.\""
license: MIT
---

# Store Price Tracker jobs

Each section below walks through one job with the tools of the `store-prices` MCP server. The same recipes are MCP prompts (prompts/list) on `https://api.openkrill.app/gateway/mcp`.
Connect the server at `https://stores.openkrill.app/mcp` in your MCP client settings (remote streamable HTTP, no key), then call its tools as normal tool calls. They are not command line programs: Bash, curl and scripts cannot reach them.

## Check a store's products and price changes

Job: Check a store's products and price changes, with the Store Price Tracker MCP server.

Use the `check_store_prices` tool for this job.

Work on the user's request. If there is none yet, ask what they need. A request this job handles: "Track competitor prices on allbirds.com."

Steps:
1. Call `check_store_prices` as a normal MCP tool call, with the request's values in the fields of its inputSchema. It needs `stores`.
2. If a value the tool needs is missing and you cannot tell it from the request, ask the user one short question first.
3. This input is known to work; copy its format, not its values: `{"stores":["allbirds.com"]}`
4. For the request "Track competitor prices on allbirds.com.", a correct answer looks like this: One store entry, status ok, with the snapshot date, product count, currency and a list of products with prices and availability; the first call for a store has no changes yet.
5. Follow the server's own rules:
   - Use check_store_prices when the user asks what an online store sells, what it charges, or what changed on it; pass each store's web address as the user wrote it, up to five.
   - All three tools add a store they read to the daily snapshot list.
   - The first read of a store has no changes: say that changes show up from the next daily snapshot.
   - Link each product's url and never guess prices.
   - Only Shopify stores with a public product feed can be read.
   - Next step by status: invalid, ask for the store address, such as allbirds.com; unavailable, relay the message and do not retry the same store in this chat; stale, show the data and say it is from the last snapshot; not_found, ask for the product link; ambiguous, show the candidates and call again with the title the user picks; no_matches, follow the message (another match_by, a shorter query or a lower min_gap_pct); partial, say that some products may be missing.
6. If the call fails or the answer looks wrong, tell the user, then report it with `submit_feedback` (kind bug, tool `check_store_prices`).

## Compare prices and find gaps across stores

Job: Compare prices and find gaps across stores, with the Store Price Tracker MCP server.

Use the `compare_store_prices` tool for this job.

Work on the user's request. If there is none yet, ask what they need. A request this job handles: "Compare product prices on mysneakerstore.com with allbirds.com and find products with at least 15% price gap."

Steps:
1. Call `compare_store_prices` as a normal MCP tool call, with the request's values in the fields of its inputSchema. It needs `source_store`, `target_store`.
2. If a value the tool needs is missing and you cannot tell it from the request, ask the user one short question first.
3. This input is known to work; copy its format, not its values: `{"source_store":"allbirds.com","target_store":"allbirds.ca"}`
4. For the request "Compare product prices on mysneakerstore.com with allbirds.com and find products with at least 15% price gap.", a correct answer looks like this: A price gap report listing matching products with their price difference, percentage spread, and stock availability.
5. Follow the server's own rules:
   - Use compare_store_prices to compare prices between two stores, find price gaps or margins, or see which store sells an item cheaper.
   - All three tools add a store they read to the daily snapshot list.
   - The first read of a store has no changes: say that changes show up from the next daily snapshot.
   - Link each product's url and never guess prices.
   - Only Shopify stores with a public product feed can be read.
   - Next step by status: invalid, ask for the store address, such as allbirds.com; unavailable, relay the message and do not retry the same store in this chat; stale, show the data and say it is from the last snapshot; not_found, ask for the product link; ambiguous, show the candidates and call again with the title the user picks; no_matches, follow the message (another match_by, a shorter query or a lower min_gap_pct); partial, say that some products may be missing.
6. If the call fails or the answer looks wrong, tell the user, then report it with `submit_feedback` (kind bug, tool `compare_store_prices`).

## Get a product's price history

Job: Get a product's price history, with the Store Price Tracker MCP server.

Use the `get_product_price_history` tool for this job.

Work on the user's request. If there is none yet, ask what they need. A request this job handles: "How has the price of the Allbirds Tree Runner changed over time?"

Steps:
1. Call `get_product_price_history` as a normal MCP tool call, with the request's values in the fields of its inputSchema. It needs `store`, `product`.
2. If a value the tool needs is missing and you cannot tell it from the request, ask the user one short question first.
3. This input is known to work; copy its format, not its values: `{"store":"allbirds.com","product":"Men's Tree Runner - Jet Black (Black Sole)"}`
4. For the request "How has the price of the Allbirds Tree Runner changed over time?", a correct answer looks like this: A product history with per-variant points (day, price, compare-at price, availability), or a list of matching titles to choose from.
5. Follow the server's own rules:
   - Use get_product_price_history when the user asks how one product's price or stock moved; pass the store and the product's link, handle or title.
   - All three tools add a store they read to the daily snapshot list.
   - The first read of a store has no changes: say that changes show up from the next daily snapshot.
   - Link each product's url and never guess prices.
   - Only Shopify stores with a public product feed can be read.
   - Next step by status: invalid, ask for the store address, such as allbirds.com; unavailable, relay the message and do not retry the same store in this chat; stale, show the data and say it is from the last snapshot; not_found, ask for the product link; ambiguous, show the candidates and call again with the title the user picks; no_matches, follow the message (another match_by, a shorter query or a lower min_gap_pct); partial, say that some products may be missing.
6. If the call fails or the answer looks wrong, tell the user, then report it with `submit_feedback` (kind bug, tool `get_product_price_history`).