Five Below MCP server for AI agents
Let Claude, ChatGPT or your own agent read Five Below: 1 typed function through one MCP server. No Five Below API key needed.
- Site
- fivebelow.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Five Below
An MCP server for Five Below 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/fivebelowEvery site
One MCP server for Five Below 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 fivebelow.com's catalog for a keyword and returns matching products.Arguments
Name Type Required args{ query: string, limit?: number, page?: number }Yes Returns
FiveBelowSearchResultsinterface FiveBelowVariant { sku: string | null; style: string | null; price: number | null; inventory: number | null; available: boolean; } interface FiveBelowSearchResult { objectID: string; name: string; url: string; image: string | null; priceMin: number | null; priceMax: number | null; variants: FiveBelowVariant[]; inStock: boolean; } interface FiveBelowSearchResults { query: string; page: number; totalMatches: number | null; totalPages: number | null; results: FiveBelowSearchResult[]; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/fivebelow/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.fivebelow.search({ query: "slime" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.fivebelow.search({"query": "slime"}))curl -X POST https://api.bowmark.ai/v1/sites/fivebelow/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"slime"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.fivebelow.search({ query: "slime" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/fivebelow/<function> - OpenAPI
/v1/sites/fivebelow/openapi.json