Zepto MCP server for AI agents
Let Claude, ChatGPT or your own agent read Zepto: 2 typed functions through one MCP server. No Zepto API key needed.
- Site
- zepto.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Zepto
An MCP server for Zepto 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/zeptoEvery site
One MCP server for Zepto 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
productReads a Zepto product page (www.zepto.com/pn/<slug>/pvid/<id>) and returns its name, brand, selling price and MRP in rupees, stock, pack size…Arguments
Name Type Required args{ url: string } | { id: string }Yes Returns
ZeptoProductinterface ZeptoProduct { id: string; productId: string | null; name: string; brand: string | null; price: number | null; mrp: number | null; currency: string; inStock: boolean | null; size: string | null; category: string | null; rating: number | null; ratingCount: number | null; description: string | null; images: string[]; url: string }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/zepto/productCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.zepto.product({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.zepto.product({}))curl -X POST https://api.bowmark.ai/v1/sites/zepto/product \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.zepto.product({});searchSearches Zepto's grocery catalogue and returns each product card's name, current product-page price and MRP in rupees, pack size, stock and product…Arguments
Name Type Required args{ query: string }Yes Returns
ZeptoSearchRow[]interface ZeptoSearchRow { id: string; name: string; price: number | null; mrp: number | null; packSize: string | null; inStock: boolean | null; url: string }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/zepto/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.zepto.search({ query: "tata salt" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.zepto.search({"query": "tata salt"}))curl -X POST https://api.bowmark.ai/v1/sites/zepto/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"tata salt"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.zepto.search({ query: "tata salt" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/zepto/<function> - OpenAPI
/v1/sites/zepto/openapi.json