Start free

Platforms MCP server

MCP server · 2 tools · 1 endpoint

Google Shopping MCP server

One endpoint, one job: search Google Shopping for a product and get back listings with merchants and prices.

Get a free key Connect in a minute

100 credits on signup · No card · Sign in with OAuth or paste a key

scrapersocial-google_shopping mcp.scrapersocial.com/google_shoppingconnected
you

Search Google Shopping for <product name> and list every merchant with its price, cheapest first

agent
calls list_endpoints free
server
endpoints [{ path, input, credits }] · /v1/google_shopping/product-search is 3 credits
agent
calls call_endpoint 3 credits · the endpoint's own cost
{ "path": "/v1/google_shopping/product-search", "query": "<keywords>" }
server
returns
product object · the full product record
Shape only. Keys follow the tool's summary; a real call returns the full record. 2 calls · 3 credits

Connect

One URL. Your client already knows what to do with it.

The first call opens a sign-in. New accounts get 100 credits, no card. Every client below shares one account and one balance.

Get a free key
server url https://mcp.scrapersocial.com/google_shopping
claude.aiOAuth

Settings → Connectors → Add custom connector, then paste the server URL.

mcp.scrapersocial.com/google_shopping

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

$ claude mcp add --transport http scrapersocial-google_shopping https://mcp.scrapersocial.com/google_shopping

Approve the sign-in prompt on first use.

Cursorone click

Installs the server and opens the MCP panel.

Add to Cursor
or paste the JSON into .cursor/mcp.json
{ "mcpServers": { "scrapersocial-google_shopping": { "url": "https://mcp.scrapersocial.com/google_shopping", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Other clients · VS Code, Windsurf, Gemini CLI, anything that speaks MCP
VS Codeone click or JSON
Add to VS Codeor run MCP: Add Server, choose HTTP and use:
{ "name": "scrapersocial-google_shopping", "type": "http", "url": "https://mcp.scrapersocial.com/google_shopping" }
Windsurf~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "scrapersocial-google_shopping": { "serverUrl": "https://mcp.scrapersocial.com/google_shopping", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Gemini CLI~/.gemini/settings.json
{ "mcpServers": { "scrapersocial-google_shopping": { "httpUrl": "https://mcp.scrapersocial.com/google_shopping", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Any clientStreamable HTTP · OAuth 2.1 or Bearer
$ npx add-mcp https://mcp.scrapersocial.com/google_shopping

One account and one balance across every client and the every-platform hub at mcp.scrapersocial.com.

What it does

What your agent can do with Google Shopping

This spoke returns one thing: the products Google Shopping lists for a keyword, each with its merchant and price. That’s the whole surface, and it’s enough for most price-comparison work.

There is no capability tool on this spoke; the two tools are list_endpoints and call_endpoint. The first shows the single live path and what it accepts. The second runs it: call_endpoint with path: /v1/google_shopping/product-search and a query. You get back a list of products with the merchant offering each one and the price shown in the shopping index, up to 50 per call, with a cursor if there are more.

Google Shopping is an aggregator rather than a social platform, and to ScraperSocial it is public web data, nothing more. The agent sees what a visitor searching the shopping tab would see, as JSON, with no account involved.

Each product returned costs 3 credits. Ask for ten and you pay 30; ask for the first five and you pay 15. A query that matches nothing still costs 1.

Connect https://mcp.scrapersocial.com/google_shopping, then type the thing you want priced. The agent calls the endpoint and reads the merchant list back to you.

Four jobs it finishes on its own

01

Price checks across merchants

Give the agent a product name and ask which merchants list it and for how much. It calls the search, sorts by price, and tells you the spread. For a shortlist of SKUs that's a few minutes a day instead of a browser session.

02

Watching your own price position

Search for your product on a schedule and record where your listing sits against the others. If a competitor drops below you, the agent can say so the same morning.

03

Market scans before a launch

Query the category you're thinking of entering and look at the price band and the merchants already in it. Fifty results cost 150 credits, which is a cheap first look.

04

Enriching a catalogue

For a spreadsheet of product names, have the agent run each through `/v1/google_shopping/product-search` and fill in the lowest listed price and the merchant. Set a small limit per query to keep the cost predictable.

Limits · read before you connect

What this does not do

Written by a person, not generated. If something here is wrong, tell us.

Search is the only endpoint. There’s no way to open a single product by id, read a product’s reviews or list its sellers on this spoke; if you need one merchant’s listing in depth, the Amazon and TikTok Shop spokes cover theirs. Prices are what the shopping index showed when the page was read; results may be served from cache, and fresh: true forces a new read at the same 3 credits per product. Nothing here is live inventory, and the server can’t click through to a merchant, add to a cart or see Merchant Center data for your store. Results come back 50 at a time with a cursor.

Tools

2 tools, and one endpoint behind them

Google Shopping has one endpoint, so there is nothing to wrap. list_endpoints tells the agent the path; call_endpoint runs it at the endpoint's own price.

Full credit table →

List every Google Shopping endpoint

list_endpoints

Browse every Google Shopping endpoint, its input and its credit cost. Free, and calls nothing upstream.

free

Call any Google Shopping endpoint by path

call_endpoint

Run any Google Shopping endpoint by its path, so nothing Google Shopping offers is out of reach of an agent.

endpoint's own cost
What list_endpoints returns
/v1/google_shopping/product-search · input: query 3 credits / product

Pricing

100 free credits is 33 Google Shopping products.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Every call costs 3 credits.

33 Google Shopping products/v1/google_shopping/product-search · 3 each
Get a free key 100 credits on signup · $5 for 1,000 · full credit table

Prompts

Things to ask once it is connected

Copy one, swap the placeholder, paste it into your client.

Search Google Shopping for <product name> and list every merchant with its price, cheapest first

What's the price range for <product name> right now? Give me min, median and max

Find <product name> on Google Shopping and tell me if anyone lists it under <price>

Run a Google Shopping search for <keyword> with limit 10 and show the results as a table

Check these five products and return the lowest merchant price for each: <list>

Questions

Before you connect

What does a search cost? #

3 credits per product returned. The default page size is 20, so an unbounded query costs about 60; set `limit` lower when you only need the top few. Signup includes 100 free credits; after that, $5 buys 1,000.

Can I look up a single product by id? #

Not through this server. Product detail, product reviews and seller lists aren't offered for Google Shopping; search is the whole surface.

Are the prices current? #

They're what the shopping index displayed at the moment the page was read, and the response may be cached. Pass `fresh: true` when the exact figure matters; it costs the same.

Is ScraperSocial connected to Google? #

No. It's an independent company reading public Google Shopping result pages. There is no partnership, and Merchant Center data isn't accessible.

Can the agent buy the product? #

No. It reads listings and returns them. Purchases, carts and merchant checkout pages are out of scope.