Google Autocomplete Keyword Expansion Scraper: MCP config, n8n workflow and API

{
  "keywords": [
    "python tutorial"
  ],
  "mode": "exact",
  "country": "US",
  "language": "en",
  "source": "web",
  "maxItems": 3,
  "maxSuggestionsPerSeed": 3,
  "outputFormat": "flat",
  "expansionDepth": "0",
  "dedupeAcrossSeeds": false,
  "includeIntent": false
}

---
name: google-autocomplete-keyword-expansion-scraper
description: "Keyword suggestions with seed, expansion type, position, locale, source URL, Google relevance and optional recursion depth. Runs the Apify Actor dataspryva/google-autocomplete-keyword-expansion-scraper. Use when the user needs Google Search data with fields such as keyword, seed, type, position, locale, relevance 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: "dataspryva/google-autocomplete-keyword-expansion-scraper"
  store-url: "https://apify.com/dataspryva/google-autocomplete-keyword-expansion-scraper"
---

# Google Autocomplete Keyword Expansion Scraper

Use this skill to fetch Google Search data with the Apify Actor `dataspryva/google-autocomplete-keyword-expansion-scraper` 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 |
| --- | --- | --- |
| `keywords` | array, required | One or more seeds. 1-3 word seeds return the most suggestions. Each seed is expanded according to `mode`. |
| `mode` | one of `all`, `exact`, `alphabet`, `questions`, `modifiers`, `prepositions`, `comparisons`, `related` | How each seed is expanded. `all` runs every strategy; `exact` queries only the seed; `alphabet` adds a-z and 0-9 before and after; `questions` uses locale question words; `modifiers` adds prepositions and buyer-intent words; `related` adds trailing-space… |
| `country` | string | Google market used for the `gl` parameter. Changes ranking and local phrasing. 134 markets were verified against the live endpoint; the legacy `ALL` value maps to US. |
| `language` | string | Language used for the `hl` parameter and for the locale-aware question and modifier words. 19 languages have native expansion vocabularies; the rest fall back to English modifiers. |
| `source` | one of `web`, `youtube`, `shopping`, `all` | Which Google autocomplete surface to query: web, YouTube or Shopping. `all` runs all three and multiplies the request count. |
| `maxItems` | integer | Hard cap on dataset records across all seeds and sources. Flat mode counts suggestions; tree mode counts one record per seed/source. |
| `maxSuggestionsPerSeed` | integer | Cap on suggestions collected for one seed, applied after all expansion queries have run. Defaults to 2,000 when omitted (legacy maxItemsPerKeyword is honoured). |
| `outputFormat` | one of `flat`, `tree` | `flat` emits one row per suggestion. `tree` emits one row per seed and source with a nested suggestions array (the legacy shape). |
| `expansionDepth` | one of `0`, `1`, `2` | Re-query the first 15 discovered suggestions to go one or two levels deeper. Off for the cheapest run. |
| `dedupeAcrossSeeds` | boolean | Emit a phrase only once per run. Off keeps every seed complete; on removes overlaps between seeds. |
| `includeIntent` | boolean | Add a deterministic intent tag (question, comparison, local, transactional, commercial, informational) where a language vocabulary matches. |

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

```json
{
  "keywords": [
    "python tutorial"
  ],
  "mode": "exact",
  "country": "US",
  "language": "en",
  "source": "web",
  "maxItems": 3,
  "maxSuggestionsPerSeed": 3,
  "outputFormat": "flat",
  "expansionDepth": "0",
  "dedupeAcrossSeeds": false,
  "includeIntent": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/dataspryva~google-autocomplete-keyword-expansion-scraper/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/dataspryva~google-autocomplete-keyword-expansion-scraper/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: `keyword`, `seed`, `type`, `position`, `locale`, `relevance`, `source`.

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