Canada Computers MCP server for AI agents
Let Claude, ChatGPT or your own agent read Canada Computers: 1 typed function through one MCP server. No Canada Computers API key needed.
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Canada Computers
An MCP server for Canada Computers alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/canadacomputersEvery site
One MCP server for Canada Computers and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
searchSearches canadacomputers.com (Canada Computers & Electronics) for a product, e.g. "rtx 5070", and returns the first page of matches: title, SKU…Arguments
Name Type Required argsCanadaComputersSearchArgs | stringYes interface CanadaComputersSearchArgs { query: string; limit?: number; }Returns
CanadaComputersSearchResultinterface CanadaComputersProduct { id: string; sku: string | null; title: string; url: string; imageUrl: string | null; /** CAD, the price the shopper pays today. */ price: number | null; regularPrice: number | null; onSale: boolean; /** Orderable online (ships or backorders). */ availableOnline: boolean; /** In stock at one or more Canada Computers stores for pickup. */ availableInStore: boolean; /** The site's own label, e.g. "Online - Available to Ship", "Online - Sold Out". */ onlineStatus: string | null; /** e.g. "In Store - Available for Pickup", "In Store - Sold Out". */ inStoreStatus: string | null; /** Every query word is in the title or SKU. The site's search is fuzzy and returns * near-misses (5070s for "rtx 4070 super") unmarked, filter on this before trusting a row. * Literal, so a real match whose title omits a word ("MSI G5070-12S2C" for "rtx 5070") is false. */ matchesQuery: boolean; } interface CanadaComputersSearchResult { query: string; searchUrl: string; /** The site's own result count. 0 = the store carries nothing for this query, and * products is [] (no error). */ totalResults: number | null; products: CanadaComputersProduct[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/canadacomputers/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.canadacomputers.search({ query: "rtx 5070" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.canadacomputers.search({"query": "rtx 5070"}))curl -X POST https://api.bowmark.ai/v1/sites/canadacomputers/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"rtx 5070"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.canadacomputers.search({ query: "rtx 5070" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/canadacomputers/<function> - OpenAPI
/v1/sites/canadacomputers/openapi.json