Publix MCP server for AI agents
Let Claude, ChatGPT or your own agent read Publix: 4 typed functions through one MCP server. No Publix API key needed.
- Site
- publix.com
- Functions
- 4
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Publix
An MCP server for Publix 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/publixEvery site
One MCP server for Publix 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 4
searchStoresFinds Publix supermarket stores near a city and state or a ZIP code, as the publix.com store locator lists them: store number, name, address, store…Arguments
Name Type Required citystringNo statestringNo zipstringNo limitnumberNo radiusMilesnumberNo Returns
PublixStoreSearchResponseinterface PublixHours { openTime: string | null; closeTime: string | null; isOpen24Hours: boolean; isClosed: boolean; reason: string | null } interface PublixStore { storeNumber: string; name: string; type: string | null; address: { street: string | null; city: string | null; state: string | null; zip: string | null }; phones: { store: string | null; pharmacy: string | null; eventPlanning: string | null }; latitude: number | null; longitude: number | null; distance: number | null; timeZone: string | null; hours: PublixHours[]; departments: string[]; services: string[]; secondaryLocations: { name: string; phone: string | null; hours: PublixHours[] }[]; image: string | null; url: string } interface PublixStoreSearchResponse { stores: PublixStore[]; correctedSearchTerm: string | null }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/publix/searchStoresCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.publix.searchStores({ city: "Miami", state: "FL", limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.publix.searchStores({"city": "Miami", "state": "FL", "limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/publix/searchStores \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"city":"Miami","state":"FL","limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.publix.searchStores({ city: "Miami", state: "FL", limit: 3 });storeReturns one Publix store by its store number, as the publix.com store page shows it: address, phones, coordinates, the next seven days of hours…Arguments
Name Type Required storeNumberstringYes Returns
PublixStoreinterface PublixHours { openTime: string | null; closeTime: string | null; isOpen24Hours: boolean; isClosed: boolean; reason: string | null } interface PublixStore { storeNumber: string; name: string; type: string | null; address: { street: string | null; city: string | null; state: string | null; zip: string | null }; phones: { store: string | null; pharmacy: string | null; eventPlanning: string | null }; latitude: number | null; longitude: number | null; distance: number | null; timeZone: string | null; hours: PublixHours[]; departments: string[]; services: string[]; secondaryLocations: { name: string; phone: string | null; hours: PublixHours[] }[]; image: string | null; url: string }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/publix/storeCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.publix.store({ storeNumber: "1614" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.publix.store({"storeNumber": "1614"}))curl -X POST https://api.bowmark.ai/v1/sites/publix/store \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"storeNumber":"1614"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.publix.store({ storeNumber: "1614" });suggestionsReturns the search type-ahead suggestions the publix.com grocery search box shows for a partial keyword, optionally scoped to one store.Arguments
Name Type Required keywordstringYes storeNumberstringNo Returns
PublixSuggestionsResponseinterface PublixSuggestionsResponse { keyword: string; suggestions: string[] }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/publix/suggestionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.publix.suggestions({ keyword: "chicken" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.publix.suggestions({"keyword": "chicken"}))curl -X POST https://api.bowmark.ai/v1/sites/publix/suggestions \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"keyword":"chicken"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.publix.suggestions({ keyword: "chicken" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/publix/<function> - OpenAPI
/v1/sites/publix/openapi.json