Google Shopping Price Comparison & Deal Finder: MCP config, n8n workflow and API

Product listings and product-viewer records with real product IDs, viewer URLs, seller offers, shipping and totals, price ranges, specifications and 12-month price history where Google exposes it.

Fastest route, in Claude Code:

claude mcp add --transport http google-shopping-price-comparison-and-deal-finder "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder"

One click, signs in with Apify on first use:

Any other client, one command (writes the config for 25+ agents, including Windsurf, Zed, Cline and Goose):

npx add-mcp "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder" --name google-shopping-price-comparison-and-deal-finder

Every file on this page is generated from the Actor's published schema: 51 of 51 checks pass (validated, not run)
  • MCP configs: 7 of 7 (Uses Apify's hosted MCP endpoint over HTTPS; The tools parameter lists exactly the chosen Actors as owner/name; JSON configs parse and use the client's top-level key and the same URL; Codex TOML has a [mcp_servers.<name>] table with url and bearer_token_env_var; CLI commands quote the same URL and use the streamable HTTP transport; One-click install links decode back to the same URL and carry no token; Only placeholders, no real token)
  • n8n workflow: 11 of 11 (It has a nodes array and a connections object; Every node has a name, type, typeVersion, position and parameters; Node names are unique; Every node type is a known n8n core node (or the Apify node); Every node uses a typeVersion that n8n ships; Every connection points at an existing node; At least one trigger starts the workflow; Every working node is reachable from a trigger; Apify calls use POST and a credential for the token; Actor input matches the Actor's published input schema; No token or credential value is embedded)
  • long-run workflow: 11 of 11 (It has a nodes array and a connections object; Every node has a name, type, typeVersion, position and parameters; Node names are unique; Every node type is a known n8n core node (or the Apify node); Every node uses a typeVersion that n8n ships; Every connection points at an existing node; At least one trigger starts the workflow; Every working node is reachable from a trigger; Apify calls use POST and a credential for the token; Actor input matches the Actor's published input schema; No token or credential value is embedded)
  • example input: 5 of 5 (The schema has no required fields; Every input key exists in the published input schema; Every value has the type the schema declares; Every choice field uses one of its published options; Numbers respect the published minimum and maximum)
  • code snippets: 4 of 4 (curl calls the documented run-sync-get-dataset-items endpoint for this Actor; Python (apify-client 3.x typed Run) and JavaScript use the official apify-client call() then read the run's dataset; Multi-line shell commands continue every line with a backslash; Token read from APIFY_TOKEN, none embedded)
  • SKILL.md: 13 of 13 (SKILL.md starts with YAML front matter; name is 1-64 lowercase letters, digits and single hyphens; name matches the skill folder name; description is present, at most 1024 characters and has no angle brackets; front matter uses only spec fields; compatibility is at most 500 characters; body has instructions; field descriptions end on whole sentences; no credential values are embedded; the token is read from APIFY_TOKEN; the run command calls this Actor's run-sync endpoint; the example input is valid JSON; the example input matches the published input schema)

What the checks cover

What a run costs

Every run pays a start fee plus a price per result. On the Free plan this Actor's start fee is $0.40 (the start event, $0.10 per GB, times its default 4 GB of memory), $0.12 on Business; results cost $0.99 per 1,000 results (pay per event). Checked 2026-11-12.

Results in one runStartResultsRun total
10$0.40$0.010$0.41
100$0.40$0.10$0.50
1,000$0.40$0.99$1.39

Plus Apify platform usage for the run, which the caller pays. A smaller memory setting lowers the start fee if the Actor still finishes. Prices can change; the Store pricing tab is the source of truth.

MCP config

One URL works in every client: https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder. It exposes this Actor as a tool, plus fetch-actor-details so the agent can read the input schema before calling it. Pick your client:

Claude Code configterminal or .mcp.json

claude mcp add --transport http google-shopping-price-comparison-and-deal-finder "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder"

Run the command in your project folder. Add --scope user to make it available in every project. Full Claude Code setup

Tools your agent gets

Listed by Apify's MCP server 0.21.5 for this exact URL on 2026-11-11 (a tools/list call; nothing was run).

  • fetch-actor-detailsreads the input schema
  • vexaloom-labs--google-shopping-price-comparison-and-deal-finderruns the Actor and returns its results
  • get-actor-runchecks a run's status
  • get-dataset-itemsreads a run's results
  • get-key-value-store-recordreads a stored record such as a file or summary
  • abort-actor-runstops a run that is still going

n8n workflow

A manual and a daily trigger call the Actor through the HTTP Request node with your Apify token, then hand each record to the destination you pick. The Actor input sits in the request body, already filled with the example below.

Send the records to
  • Run by hand
  • Every day
  • Run Apify Actor

n8n workflowgoogle-shopping-price-comparison-and-deal-finder.n8n.json

Actor on Apify
{
  "name": "Google Shopping Price Comparison & Deal Finder to n8n only",
  "nodes": [
    {
      "id": "265b81fa-b162-4374-af83-3f7d4c7131f3",
      "name": "Run by hand",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        0,
        0
      ],
      "parameters": {}
    },
    {
      "id": "56f6571a-b892-4242-a71f-814377d8b8fb",
      "name": "Every day",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.2,
      "position": [
        0,
        200
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "triggerAtHour": 8
            }
          ]
        }
      },
      "notes": "Activate the workflow to run on this schedule."
    },
    {
      "id": "f181329e-2e14-4ee7-ade8-030a582489d3",
      "name": "Run Apify Actor",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        260,
        100
      ],
      "parameters": {
        "method": "POST",
        "url": "https://api.apify.com/v2/actors/vexaloom-labs~google-shopping-price-comparison-and-deal-finder/run-sync-get-dataset-items",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "{\n  \"mode\": \"search\",\n  \"queries\": [\n    \"iPhone 15 Pro Max\"\n  ],\n  \"countryCode\": \"us\",\n  \"languageCode\": \"en\",\n  \"onSale\": false,\n  \"freeShipping\": false,\n  \"maxResultsPerQuery\": 1,\n  \"includePriceHistory\": false,\n  \"includeProductDetails\": false\n}",
        "options": {
          "timeout": 310000
        }
      },
      "notes": "Actor: vexaloom-labs/google-shopping-price-comparison-and-deal-finder. Select a Header Auth credential: name Authorization, value Bearer + your Apify token. Edit the JSON body to change the input.",
      "notesInFlow": false
    },
    {
      "id": "94bf0302-e06d-4292-a8b3-f8371854811f",
      "name": "Setup",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        0,
        -370
      ],
      "parameters": {
        "content": "## Google Shopping Price Comparison & Deal Finder\n\nSource: [vexaloom-labs/google-shopping-price-comparison-and-deal-finder](https://apify.com/vexaloom-labs/google-shopping-price-comparison-and-deal-finder) on Apify.\n\n1. In **Run Apify Actor**, create a Header Auth credential: name `Authorization`, value `Bearer YOUR_APIFY_TOKEN` with your token.\n2. Click **Execute workflow**. Each record arrives as one n8n item.\n3. Edit the JSON body of **Run Apify Actor** to change the input.\n\nGenerated by recipeforagents.com. Validated, not executed: runs are billed to your Apify account.",
        "height": 340,
        "width": 460,
        "color": 6
      }
    }
  ],
  "connections": {
    "Run by hand": {
      "main": [
        [
          {
            "node": "Run Apify Actor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Every day": {
      "main": [
        [
          {
            "node": "Run Apify Actor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "pinData": {},
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "meta": {
    "templateCredsSetupCompleted": false
  },
  "tags": []
}

Import with Workflows, Import from file, or paste into the canvas. Credentials are not included: you select them after import.

All 7 destination variants pass the same checks at build time. Built-in nodes only, at versions n8n has shipped since 1.80: they import on n8n Cloud and older self-hosted instances without community nodes. Prefer Apify's own node? The verified community node @apify/n8n-nodes-apify runs the same Actor with OAuth sign-in on n8n Cloud.

Runs longer than 5 minutes? The synchronous endpoint answers HTTP 408 after 300 seconds. The long-run variant starts the run, checks it every minute until it ends, then reads its dataset (HTTP Request, If and Stop and Error nodes only).

Download the long-run workflow11 of 11 checks pass, not executed

Call it from code

Run the Actor from a script or your own agent framework with the Apify API. The call waits for the run to finish and returns the records. The input is the example below.

curl

API docs on Apify
curl -X POST "https://api.apify.com/v2/actors/vexaloom-labs~google-shopping-price-comparison-and-deal-finder/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"mode":"search","queries":["iPhone 15 Pro Max"],"countryCode":"us","languageCode":"en","onSale":false,"freeShipping":false,"maxResultsPerQuery":1,"includePriceHistory":false,"includeProductDetails":false}'

Example input

These values come from the Actor's Store prefill and required defaults. Change the search, URL or limit before your first run.

Actor inputinput.json

{
  "mode": "search",
  "queries": [
    "iPhone 15 Pro Max"
  ],
  "countryCode": "us",
  "languageCode": "en",
  "onSale": false,
  "freeShipping": false,
  "maxResultsPerQuery": 1,
  "includePriceHistory": false,
  "includeProductDetails": false
}

FieldTypeWhat it does
mode string (4 options) What to collect: keyword search, product lookup by ID/viewer URL, deals, or a department category.
queries array Product keywords for search/deals mode. Ignored in product mode; optional in category mode.
countryCode string (48 options) Country used for the Google domain, UULE location and price hint. The actual currency is always detected from the response, never relabelled.
languageCode string (27 options) Interface and result language (hl parameter).
onSale boolean Ask Google for discounted products and keep rows with an observed original price or discount.
freeShipping boolean Ask Google for free-shipping products and keep rows whose delivery text says free.
maxResultsPerQuery integer Maximum records per query (search/deals/category) or products (product mode).
includePriceHistory boolean Include per-seller daily price history when Google exposes it (product mode and search detail enrichment).
includeProductDetails boolean Fetch the product viewer for each search result to add brand, description, images, specifications and offers. Costs one extra request per result.

8 more optional fields on the Store input tab.

What your agent receives

Each run returns a list of records. The Actor publishes 46 fields, starting with title, brand, description, price.

FieldWhat it holdsFormat
queryQuerytext
position#number
recordTypeTypetext
titleProducttext
brandBrand from the product viewer.string
descriptionProduct description from the viewer.string
pricePricetext
priceValueNumeric current price.number
originalPriceOriginal or list price as displayed, when discounted.string
originalPriceValueNumeric original price.number
30 more fields
FieldWhat it holdsFormat
discountPercentObserved discount percentage.number
currencyCurrencytext
merchantMerchanttext
merchantUrlDirect seller URL when available; otherwise the Google /goto redirect. Never guessed.string
sellerDomainSeller domain when Google exposes it.string
ratingRatingtext
reviewCountReviewstext
ratingValueNumeric product rating.number
reviewCountValueNumeric product review count.integer
imageUrlPrimary product image URL.string
imageUrlsProduct image URLs from the viewer.array
deliveryDelivery text.string
shippingShipping text (e.g. Free).string
shippingValueNumeric shipping cost when known.number
availabilityAvailability text.string
conditionCondition when Google shows one.string
returnsReturns policy text.string
isSponsoredTrue only when an explicit sponsored label was observed. Not a reliable ad classifier.boolean
productIdReal Google Shopping product ID from data-pid.string
catalogIdReal Google Shopping catalog ID from data-cid; used to build viewer URLs.string
productUrlViewerlink
searchUrlURL that produced the record.string
hasMoreOffersTrue when Google reports more seller offers than the five on the viewer page.boolean
badgeObserved badge such as Best price or Low price.string
offerCountOffersnumber
offersPage Offerstext
lowestPriceLowestnumber
highestPriceHighestnumber
priceRangeLow/high price range across page offers.object
typicalPriceRangeTypicaltext

6 more fields in the full output.

Agent skill

A SKILL.md in the open Agent Skills format. It teaches Claude Code, Codex and other skill-aware agents when to call this Actor, how to build the input and how to read the result, using the API directly.

SKILL.mdgoogle-shopping-price-comparison-and-deal-finder/SKILL.md

---
name: google-shopping-price-comparison-and-deal-finder
description: "Product listings and product-viewer records with real product IDs, viewer URLs, seller offers, shipping and totals, price ranges, specifications and 12-month price history where Google exposes it. Runs the Apify Actor vexaloom-labs/google-shopping-price-comparison-and-deal-finder. Use when the user needs Google Shopping data with fields such as query, position, recordType, title, brand, description and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "vexaloom-labs/google-shopping-price-comparison-and-deal-finder"
  store-url: "https://apify.com/vexaloom-labs/google-shopping-price-comparison-and-deal-finder"
---

# Google Shopping Price Comparison & Deal Finder

Use this skill to fetch Google Shopping data with the Apify Actor `vexaloom-labs/google-shopping-price-comparison-and-deal-finder` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `mode` | one of `search`, `product`, `deals`, `category` | What to collect: keyword search, product lookup by ID/viewer URL, deals, or a department category. |
| `queries` | array | Product keywords for search/deals mode. Ignored in product mode; optional in category mode. |
| `countryCode` | string | Country used for the Google domain, UULE location and price hint. The actual currency is always detected from the response, never relabelled. |
| `languageCode` | string | Interface and result language (hl parameter). |
| `onSale` | boolean | Ask Google for discounted products and keep rows with an observed original price or discount. |
| `freeShipping` | boolean | Ask Google for free-shipping products and keep rows whose delivery text says free. |
| `maxResultsPerQuery` | integer | Maximum records per query (search/deals/category) or products (product mode). |
| `includePriceHistory` | boolean | Include per-seller daily price history when Google exposes it (product mode and search detail enrichment). |
| `includeProductDetails` | boolean | Fetch the product viewer for each search result to add brand, description, images, specifications and offers. Costs one extra request per result. |

Example `input.json` (the Actor's published prefill):

```json
{
  "mode": "search",
  "queries": [
    "iPhone 15 Pro Max"
  ],
  "countryCode": "us",
  "languageCode": "en",
  "onSale": false,
  "freeShipping": false,
  "maxResultsPerQuery": 1,
  "includePriceHistory": false,
  "includeProductDetails": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/vexaloom-labs~google-shopping-price-comparison-and-deal-finder/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/vexaloom-labs~google-shopping-price-comparison-and-deal-finder/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `query`, `position`, `recordType`, `title`, `brand`, `description`, `price`, `priceValue`, `originalPrice`, `originalPriceValue`, `discountPercent`, `currency`, `merchant`, `merchantUrl`, `sellerDomain`, `rating`, `reviewCount`, `ratingValue`, `reviewCountValue`, `imageUrl`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.

  • Claude Code: save it as ~/.claude/skills/google-shopping-price-comparison-and-deal-finder/SKILL.md, or .claude/skills/google-shopping-price-comparison-and-deal-finder/SKILL.md in a project.
  • Codex and other agents: ~/.agents/skills/google-shopping-price-comparison-and-deal-finder/SKILL.md, or .agents/skills/google-shopping-price-comparison-and-deal-finder/ in a project.
  • Or let the skills CLI place it for your agent: npx skills add https://recipeforagents.com --skill google-shopping-price-comparison-and-deal-finder
  • Set APIFY_TOKEN in the agent's environment.

Troubleshooting

Why does the client say Unauthorized or invalid token?

Every Apify Actor tool needs a signed-in Apify account. Reconnect the server so the OAuth sign-in runs again, or switch to the token variant: an Authorization: Bearer header with an API token from Apify Console, Settings, API and integrations. For a local server the token must be in the server's own env block, not only in your shell.

Source: Apify MCP server README

Why did my agent's tool list change after an update?

Without a tools parameter Apify's server loads its default tool set, which changes between releases. The URLs on this site pin the tools with ?tools=, so the agent always gets the same Actor tool plus fetch-actor-details. Apify's README gives the same advice for production.

Source: Apify MCP server README

What happens when the agent sends input the Actor rejects?

The server answers with the Actor's input schema, so the agent can fix the arguments and call again. The fetch-actor-details tool in every scoped URL lets it read that schema before the first call.

Source: Apify MCP server README

Questions

How do I connect Google Shopping Price Comparison & Deal Finder to Claude?

In Claude Code run: claude mcp add --transport http google-shopping-price-comparison-and-deal-finder "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder". In Claude Desktop or claude.ai add a custom connector with the URL https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-shopping-price-comparison-and-deal-finder and sign in to Apify. The agent then gets one tool for this Actor plus a tool that reads its input schema.

What input does Google Shopping Price Comparison & Deal Finder need?

No field is required by the published input schema. The example on this page uses the Actor's own Store prefill, so it is a sensible first run.

What does Google Shopping Price Comparison & Deal Finder cost to run?

The Apify Store lists $0.99 per 1,000 results (pay per event) for this Actor, checked 2026-11-12. Runs are billed to the Apify account whose token or sign-in the agent uses; Apify platform usage can add to that.

Which tools does the MCP config give my agent?

6 tools: fetch-actor-details, vexaloom-labs--google-shopping-price-comparison-and-deal-finder, get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run. Apify's MCP server listed them for this exact URL on 2026-11-11.