Costco MCP server for AI agents
Let Claude, ChatGPT or your own agent read Costco: 2 typed functions through one MCP server. No Costco API key needed.
- Site
- costco.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Costco
An MCP server for Costco 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/costcoEvery site
One MCP server for Costco 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 2
listGiftCardsCostco's discounted gift cards and eGift cards (restaurants, movies, games, travel).Arguments
Name Type Required options{ query?: string; limit?: number }No Returns
CostcoGiftCard[]interface CostcoGiftCard { itemNumber: string; name: string; brand: string | null; price: number | null; currency: string | null; faceValue: number | null; savings: number | null; description: string | null; image: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/costco/listGiftCardsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.costco.listGiftCards({ limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.costco.listGiftCards({"limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/costco/listGiftCards \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"options":{"limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.costco.listGiftCards({ limit: 3 });searchCostco's own search-bar autocomplete suggestions for a typed term.Arguments
Name Type Required querystringYes Returns
CostcoSearchSuggestion[]interface CostcoSearchSuggestion { term: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/costco/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.costco.search("coffee");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.costco.search("coffee"))curl -X POST https://api.bowmark.ai/v1/sites/costco/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"coffee"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.costco.search("coffee");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/costco/<function> - OpenAPI
/v1/sites/costco/openapi.json