Capital One Shopping MCP server for AI agents
Let Claude, ChatGPT or your own agent read Capital One Shopping: 2 typed functions through one MCP server. No Capital One Shopping API key needed.
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Capital One Shopping
An MCP server for Capital One Shopping 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/capitaloneshoppingEvery site
One MCP server for Capital One Shopping 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
getStoreRateReads one store's Capital One Shopping reward rate, coupon codes with success rates, deals and exclusions.Arguments
Name Type Required storestringYes Returns
CapitalOneShoppingStoreRateinterface CapitalOneShoppingCoupon { code: string; title: string | null; successRate: number | null; avgSavings: number | null; tries: number | null; lastWorkedAt: string | null; label: string | null; } interface CapitalOneShoppingDeal { title: string; url: string | null; expiration: string | null; } interface CapitalOneShoppingStoreRate { name: string; domain: string; url: string; rewardTitle: string | null; rateText: string | null; ratePercent: number | null; hasReward: boolean; exclusions: string | null; categories: string[]; coupons: CapitalOneShoppingCoupon[]; deals: CapitalOneShoppingDeal[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/capitaloneshopping/getStoreRateCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.capitaloneshopping.getStoreRate({ store: "walmart.com" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.capitaloneshopping.getStoreRate({"store": "walmart.com"}))curl -X POST https://api.bowmark.ai/v1/sites/capitaloneshopping/getStoreRate \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"store":"walmart.com"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.capitaloneshopping.getStoreRate({ store: "walmart.com" });searchStoresSearches Capital One Shopping's stores by name and returns each match's domain and cash back reward.Arguments
Name Type Required querystringYes limitnumberNo Returns
CapitalOneShoppingStore[]interface CapitalOneShoppingStore { name: string; domain: string; url: string; rateText: string | null; ratePercent: number | null; upTo: boolean; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/capitaloneshopping/searchStoresCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.capitaloneshopping.searchStores({ query: "nike" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.capitaloneshopping.searchStores({"query": "nike"}))curl -X POST https://api.bowmark.ai/v1/sites/capitaloneshopping/searchStores \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"nike"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.capitaloneshopping.searchStores({ query: "nike" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/capitaloneshopping/<function> - OpenAPI
/v1/sites/capitaloneshopping/openapi.json