Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp_canadiantire search for camping chairs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server for Canadian Tire (canadiantire.ca). It exposes the store's catalogue — product search, product detail, store-level stock and a store finder — to MCP clients such as Claude and Cursor.
Unofficial. This project is not affiliated with, endorsed by, or sponsored by Canadian Tire Corporation. It reads publicly available endpoints of canadiantire.ca for personal, noncommercial use. Respect Canadian Tire's terms of service and use responsibly.
Tool | Description |
| Product search / listings by keyword. Returns products (SKU, name, brand, model, price + sale price, rating, in-store & online stock, URL, image), total count, facets and sort options. Follows category redirects automatically. |
| Full product card by SKU: name, brand, model, description, features, images, rating/reviews, warranty, categories, specifications, and per-variant price + in-store stock with shelf/aisle location, online stock and fulfillment options. |
| In-store stock of a SKU across nearby stores, sorted in-stock first then nearest. Per store: name, address, phone, coordinates, distance, stock quantity, shelf/aisle location, pickup availability. Plus online stock. |
| Find stores nearest to a postal code or coordinates (distance-sorted with |
ct_searchParam | Type | Default | Notes |
| string | — | Search keyword (required). |
| string |
| Store id for store-specific stock/pricing. |
|
|
| Response language. |
|
|
| Sort order. |
| int |
| 1-indexed page. |
| int (1–100) |
| Results per page. |
ct_productParam | Type | Default | Notes |
| string | — | Product code (required), e.g. |
| string | — | Postal code, e.g. |
| string |
| Store id for store-specific price/stock/shelf. Override default with |
|
|
| Response language. |
ct_store_availabilityParam | Type | Default | Notes |
| string | — | Product code (required). |
| string | — | Postal code; nearby stores are taken around it (overrides |
| string |
| Reference store; nearby stores are taken around it. |
|
|
| Response language. |
| int (1–25) |
| Max number of stores to check. |
Default store: product/availability tools default to store
676(Edmonton Windermere, AB). SetCT_DEFAULT_STORE, or passstoreId/postalCode, to use your local store. Usect_storeswith a postal code to find the right store id.
ct_storesParam | Type | Default | Notes |
| string | — | Canadian postal code, e.g. |
| number | — | Alternative to |
|
|
| Response language. |
| int (1–50) |
| Max stores to return. |
The store API geosorts by coordinates only (no postal-code search), so a postal code is first geocoded via
api.zippopotam.us(free, no key).distanceKmis returned by Canadian Tire.
Related MCP server: DigiKey MCP Server
canadiantire.ca/api/* is gated by an Azure API Management subscription key — the
ocp-apim-subscription-key header. With that key, requests succeed over a plain Node
fetch: no cookies, no Akamai _abck, and no TLS (JA3) fingerprinting to work around
(unlike some other retailers). So this server talks to the API directly with fetch —
no curl subprocess required.
The key is a public client key embedded in the site's JavaScript. If Canadian Tire rotates
it (calls start returning 401), set a new one via the CT_SUBSCRIPTION_KEY env var —
re-scrape it from the ocp-apim-subscription-key request header of any search XHR on
canadiantire.ca.
npm install
npm run build
npm start # runs the MCP server on stdioQuick smoke test of the search layer:
node --input-type=module -e 'import {search} from "./dist/search.js"; console.log(await search({query:"drill", pageSize:3}))'Inspect with the MCP Inspector:
npm run inspectAdd to your MCP client config (e.g. Claude Desktop claude_desktop_config.json),
pointing at the built entrypoint:
{
"mcpServers": {
"canadiantire": {
"command": "node",
"args": ["/absolute/path/to/mcp_canadiantire/dist/index.js"],
"env": {
"CT_DEFAULT_STORE": "676",
"CT_SUBSCRIPTION_KEY": "<only if the bundled key stops working>"
}
}
}
}Both env vars are optional:
CT_DEFAULT_STORE — default store id for the product/availability tools (defaults to
676, Edmonton Windermere, AB).
CT_SUBSCRIPTION_KEY — overrides the bundled Azure APIM subscription key. See below.
Every canadiantire.ca/api/* request needs an ocp-apim-subscription-key header. This is
a public client key embedded in the site's own JavaScript — not a personal secret — and
this server ships with a working value baked in, so it works out of the box with no setup.
If Canadian Tire rotates the key (requests suddenly start returning HTTP 401), grab a
fresh one and pass it via CT_SUBSCRIPTION_KEY:
Open https://www.canadiantire.ca and run any search.
In the browser dev tools Network tab, find a request to /api/v1/search/v2/search.
Copy the value of its ocp-apim-subscription-key request header.
Set it as CT_SUBSCRIPTION_KEY (env var or the client config env block above).
src/
index.ts MCP server + tool registration (stdio)
ct.ts fetch transport for canadiantire.ca (APIM key + headers)
search.ts ct_search implementation + response mapping
product.ts ct_product + ct_store_availability (productFamily + PriceAvailability APIs)
stores.ts ct_stores (store finder + postal-code geocode → nearest)PolyForm Noncommercial License 1.0.0 — free to use, modify and share for noncommercial purposes. Commercial use requires a separate license from the author.
Fetch the full product card for a Canadian Tire SKU (product code): name, brand, model, description, features, images, rating/reviews, warranty, categories, specifications, and per-variant price (current + original/sale), in-store stock with shelf/aisle location, online stock, and fulfillment options (pickup in store, ship to home, express delivery) for a given store.
| Name | Required | Description | Default |
|---|---|---|---|
| sku | Yes | Product code, e.g. '0542448P' or '054-2448-6' (from ct_search results). | |
| postalCode | No | Postal code, e.g. 'M5V 2T6'; uses the nearest store (overrides storeId). | |
| storeId | No | Store id for store-specific price/stock/shelf. Default 676. | |
| lang | No | Response language. Default 'en'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It describes what the tool returns (price, stock, etc.) but does not mention any side effects, authentication needs, rate limits, or latency. It is adequate but not enhanced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single long sentence that packs many details. It is still concise and front-loads the main purpose, but could be slightly easier to parse if broken into multiple sentences. Minor readability trade-off.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description does a good job listing the return fields (name, brand, price, stock, fulfillment, etc.). It does not cover output format or error handling, but the listed detail is sufficient for most decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds context beyond the schema, e.g., clarifying that sku is a product code from ct_search results and that postalCode overrides storeId. This adds value without being verbose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches a full product card for a Canadian Tire SKU, listing many specific data points. It distinguishes itself from sibling tools like ct_search (search) and ct_store_availability (stock check) by focusing on comprehensive single-product details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a SKU and need complete product info for a specific store. It mentions 'given a store' but does not explicitly state when not to use or how to obtain the SKU (though the SKU parameter example references ct_search results). Good but could be more explicit about prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Canadian Tire (canadiantire.ca) for products by keyword. Returns matching products with SKU, name, brand, model, price (and sale/original price), rating, in-store and online stock, URL and image, plus the total result count, available filters (facets) and sort options. Use page to paginate. When a keyword maps to a category page, categoryRedirectUrl is set.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search keyword, e.g. 'cordless drill', 'winter tires'. | |
| store | No | Store id for store-specific stock/pricing. Default 676. | |
| lang | No | Response language. Default 'en'. | |
| sort | No | Sort order. Default 'relevance'. | |
| page | No | 1-indexed page number. Default 1. | |
| pageSize | No | Results per page (1-100). Default 24. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return fields (SKU, name, price, stock, etc.), total count, filters, and sort options, implying read-only behavior. No side effects are mentioned, but the description is sufficient for understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences: purpose, return fields, and special behavior. It is front-loaded with the main action, and every sentence adds necessary information without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, no output schema, and no annotations, the description covers the main functionality: search, pagination, category redirects, and return fields. It could mention error handling or rate limits, but it is complete enough for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 100%, but the description adds value beyond the schema: it explains how to use 'page' for pagination and describes the 'categoryRedirectUrl' field. This provides meaningful context on usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search Canadian Tire... for products by keyword.' The verb is specific (search), the resource is defined (Canadian Tire products), and it distinguishes from sibling tools (ct_product for single product, ct_store_availability for stock, ct_stores for store list).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains how to use it: search by keyword, paginate with 'page', and notes category redirect behavior. It does not explicitly mention when not to use or alternatives (e.g., use ct_product for specific product details), but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check in-store stock of a Canadian Tire SKU across nearby stores. Returns, per store: store name, address, phone, coordinates, distance, in-store stock quantity, shelf/aisle location, and pickup availability — sorted in-stock first, then nearest. Also reports online (Corporate) stock. Use to answer 'which store has this in stock near me'.
| Name | Required | Description | Default |
|---|---|---|---|
| sku | Yes | Product code, e.g. '0542448P'. | |
| postalCode | No | Postal code, e.g. 'M5V 2T6'; nearby stores are taken around it (overrides storeId). | |
| storeId | No | Reference store; nearby stores are taken around it. Default 676. | |
| lang | No | Response language. Default 'en'. | |
| limit | No | Max number of stores to check (1-25). Default 10. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description details the tool's behavior: returns sorted list, includes online stock, and lists output fields. It does not disclose potential side effects or authorization needs, but for a read-only tool this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the main action and output summary, no wasted words. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains output structure and usage context well. Missing details on error handling or data freshness, but overall adequate given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with good parameter descriptions. The description adds overall context (e.g., sorting, online stock) but does not significantly enhance individual parameter meaning beyond the schema, maintaining baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks in-store stock of a Canadian Tire SKU across nearby stores, listing returned fields and sorting. It directly addresses a user question, distinguishing itself from sibling tools like ct_product, ct_search, and ct_stores.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use it to answer 'which store has this in stock near me', providing clear context. However, it does not mention when not to use it or compare with alternatives, missing some guidance against sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find Canadian Tire stores nearest to a postal code or coordinates, sorted by distance (with distanceKm). Each store: id, name, address, town, province, postal code, phone, coordinates, URL, services, and fulfillment eligibility (free pickup / curbside / express delivery). Use to find a store id for ct_product / ct_store_availability.
| Name | Required | Description | Default |
|---|---|---|---|
| postalCode | No | Canadian postal code, e.g. 'M5V 2T6'. Geocoded, then distance-sorted. | |
| latitude | No | Latitude (alternative to postalCode). | |
| longitude | No | Longitude (used with latitude). | |
| lang | No | Response language. Default 'en'. | |
| limit | No | Max stores to return (1-50). Default 20. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the output structure, sorting by distance, and includes distanceKm. It does not mention destructive or side effects, which is appropriate for read-only behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action and output details, followed by usage context. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers input options (postal code/coordinates), output fields, and usage for sibling tools. Missing details on authentication or rate limits, but adequate for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter having clear descriptions. The tool description adds context like 'sorted by distance' but does not significantly enhance parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool finds Canadian Tire stores nearest to a location, sorted by distance, and lists the output fields. It distinguishes itself from siblings (ct_product, ct_search, ct_store_availability) by focusing on store finding.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear guidance by stating 'Use to find a store id for ct_product / ct_store_availability,' linking to sibling tools. It does not explicitly state when not to use, but the use case is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0ct_productct_searchct_store_availabilityct_storesScored across 4 tools
Each tool has a clearly distinct purpose: ct_product fetches full product details for a specific SKU at a store, ct_search queries products by keyword, ct_store_availability checks stock across stores for a SKU, and ct_stores finds nearby stores. No overlap in functionality.
All tool names follow a consistent 'ct_' prefix followed by a descriptive noun or noun phrase: product, search, store_availability, stores. The naming pattern is uniform and predictable.
With 4 tools, the server is well-scoped for a retail product and store information domain. Each tool serves a necessary function without redundancy or gap, covering search, details, stock, and store localization.
The tool set provides a complete surface for typical Canadian Tire interactions: product search, full product card retrieval, store stock lookup, and store finder. No obvious missing operations like category browsing or list management, which are likely out of scope.
Walmart search, product pages and customer reviews on walmart.com and walmart.ca, as JSON.
Verify Canadian deals, find the same product cheaper across .ca retailers, track CAD price history.
Canadian grocery flyer deals and recipes by item, store, postal code, cuisine, or diet. No auth.
Search 100+ US retailers, 260M+ products with real-time pricing, stock, and price history. Documentation - https://www.lemmebuyit.com/developer Homepage - https://www.lemmebuyit.com
