BeFrugal MCP server for AI agents
Let Claude, ChatGPT or your own agent read BeFrugal: 2 typed functions through one MCP server. No BeFrugal API key needed.
- Site
- befrugal.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just BeFrugal
An MCP server for BeFrugal 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/befrugalEvery site
One MCP server for BeFrugal 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 BeFrugal cash back rate from its befrugal.com/store/<slug>/ page.Arguments
Name Type Required storestringYes Returns
BefrugalStoreRateinterface BefrugalStoreRate { name: string; slug: string; url: string; available: boolean; rateText: string | null; ratePercent: number | null; upTo: boolean; wasText: string | null; wasPercent: number | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/befrugal/getStoreRateCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.befrugal.getStoreRate({ store: "macys" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.befrugal.getStoreRate({"store": "macys"}))curl -X POST https://api.bowmark.ai/v1/sites/befrugal/getStoreRate \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"store":"macys"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.befrugal.getStoreRate({ store: "macys" });searchStoresSearches BeFrugal's cash back stores by name and returns each match's slug, url and cash back rate.Arguments
Name Type Required querystringYes limitnumberNo Returns
BefrugalStore[]interface BefrugalStore { name: string; slug: string; url: string; available: boolean; rateText: string | null; ratePercent: number | null; upTo: boolean; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/befrugal/searchStoresCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.befrugal.searchStores({ query: "nike" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.befrugal.searchStores({"query": "nike"}))curl -X POST https://api.bowmark.ai/v1/sites/befrugal/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.befrugal.searchStores({ query: "nike" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/befrugal/<function> - OpenAPI
/v1/sites/befrugal/openapi.json