# Zepto MCP Server (`axlymxp/zepto-mcp-server`) Actor

MCP server + scraper for Zepto (India quick-commerce grocery). Search products, get product detail, autocomplete, and resolve stores by delivery location — live from Claude, ChatGPT, Cursor and other AI agents — or run it as a classic Zepto scraper.

- **URL**: https://apify.com/axlymxp/zepto-mcp-server.md
- **Developed by:** [axly](https://apify.com/axlymxp) (community)
- **Categories:** AI, Agents, E-commerce
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event + usage

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Zepto MCP Server

Give your AI assistant live access to **Zepto** — India's quick-commerce grocery
platform. This actor runs as a **Model Context Protocol (MCP) server** so agents
like **Claude, ChatGPT, Cursor, and n8n** can search products, pull prices and
stock, and resolve delivery stores on demand. It also works as a **classic
scraper** when run normally.

Built on Zepto's mobile API (header-only, no login, no unblocking subscription),
so keyword search returns the full priced product grid — reliably.

### MCP tools

| Tool                    | What it does                                                                                                      |
| ----------------------- | ----------------------------------------------------------------------------------------------------------------- |
| `search_zepto_products` | Search a keyword and return priced product rows for a location (name, brand, MRP, price, discount, stock, image). |
| `get_zepto_product`     | Full detail for a product-variant id at a delivery location.                                                      |
| `zepto_autocomplete`    | Search-box autocomplete suggestions for a partial query.                                                          |
| `resolve_zepto_store`   | Resolve the serving store (and serviceability) for a lat/lng or city.                                             |

Every tool is **location-scoped** — pass an Indian city name (e.g. `Mumbai`) or
explicit `latitude`/`longitude`, since Zepto prices and stock vary by store.

### Connect an AI assistant

The actor runs in **Standby mode** and speaks MCP over **Streamable HTTP** at:

```
https://<your-actor-standby-url>/mcp
```

Add it to an MCP-capable client (Claude Desktop, Cursor, etc.) as a Streamable
HTTP server, using your Apify API token as a bearer token. Then ask naturally:

> "What's the cheapest milk on Zepto in Mumbai right now?"
> "Compare Amul butter prices between Delhi and Bengaluru."

### Use cases

- **Shopping & price assistants** — let an agent answer live grocery price/stock questions.
- **Research & monitoring agents** — automate assortment and discount checks across cities.
- **Workflow automation (n8n, Make)** — wire Zepto lookups into agentic pipelines.

### Also runs as a scraper

Run the actor normally (not standby) with `searchQueries` + a `location` to push
normalized product rows to a dataset — handy for scheduled jobs and quick tests.

#### Example (normal run) input

```json
{
    "searchQueries": ["milk", "amul butter"],
    "location": "Mumbai",
    "maxPagesPerQuery": 1,
    "maxItems": 100
}
```

### Output fields

Product rows include `name`, `brand`, `pack_size`, `mrp`, `selling_price`,
`super_saver_price`, `discount_percent`, `in_stock`, `category`, `subcategory`,
`image`, `store_id`, `location_label`, and `scraped_at`. See the dataset schema
for the full list.

### FAQ

**Do I need an API key?** You connect with your Apify token as the bearer token
for the MCP endpoint. No Zepto login is required.

**Which locations work?** Any serviceable point in India — a city name or exact
coordinates.

**How fresh is the data?** Every tool call fetches live prices and stock.

**Is this legal?** You are responsible for your use of the data. Query publicly
available information and comply with Zepto's terms and applicable law.

# Actor input Schema

## `searchQueries` (type: `array`):

Keywords to search on Zepto (normal run mode only).

## `location` (type: `string`):

A known Indian city name (e.g. 'Mumbai') or 'lat,lng'. Zepto prices are store-scoped.

## `latitude` (type: `number`):

Delivery latitude (overrides 'location' when set with longitude).

## `longitude` (type: `number`):

Delivery longitude.

## `maxPagesPerQuery` (type: `integer`):

Search pages per keyword (~30 products/page).

## `maxItems` (type: `integer`):

Global cap on rows in normal run mode.

## Actor input object example

```json
{
  "searchQueries": [
    "milk",
    "amul butter"
  ],
  "location": "Mumbai",
  "maxPagesPerQuery": 1,
  "maxItems": 100
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "searchQueries": [
        "milk"
    ],
    "location": "Mumbai"
};

// Run the Actor and wait for it to finish
const run = await client.actor("axlymxp/zepto-mcp-server").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "searchQueries": ["milk"],
    "location": "Mumbai",
}

# Run the Actor and wait for it to finish
run = client.actor("axlymxp/zepto-mcp-server").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "searchQueries": [
    "milk"
  ],
  "location": "Mumbai"
}' |
apify call axlymxp/zepto-mcp-server --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=axlymxp/zepto-mcp-server",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/seavre6ZDjTPXammx/builds/qI0AG2waDwc8I9m3s/openapi.json