MCP + API · kestrel/google-autocomplete-keywords

Google Autocomplete - Keyword Suggestions & Seed Expansion

Get Google autocomplete keyword suggestions from seed queries, country and language. One row per suggestion: seed, expanded query, text, position and locale. Optional a-z seed expansion, text filters and new-only monitoring. Parsed queries are billed even when no suggestions remain.

Open Actor Download MCP config

Connect this tool

Add this URL as a remote MCP server in your client, then sign in to Apify. For a client-specific setup, use Apify's configurator.

https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/google-autocomplete-keywords
Generic MCP client configuration
{
  "mcpServers": {
    "kestrel-google-autocomplete-keywords": {
      "url": "https://mcp.apify.com?tools=call-actor,fetch-actor-details,kestrel/google-autocomplete-keywords"
    }
  }
}

Understand the output before you run

Declared dataset fields and row types · Output locations and dataset links

Use the declared dataset schema for item fields; the output schema describes where results are stored. Optional fields may be null or absent. If an integration shows a sampled schema without an optional field, check this declaration, the Actor instructions and actual returned rows before concluding that the field is unsupported.

Inspect 11 declared output fields
FieldTypeMeaning
idstring / nullid
typestring / nulltype
seedstring / nullseed
expanded_querystring / nullexpanded query
suggestionstring / nullsuggestion
positionnumber / nullposition
countrystring / nullcountry
languagestring / nulllanguage
urlstring / nullurl
changestring / nullchange
fetched_atstring / nullfetched at

Start with a small sample

Use call-actor with the JSON below. The $0.25 run ceiling is separate from the Actor input and may stop the sample early. Change the target to match your request. This input validates against build 1.0.4; it is not a promise that the source has matching rows today.

{
  "actor": "kestrel/google-autocomplete-keywords",
  "input": {
    "queries": [
      "keyword research"
    ],
    "maxSuggestionsPerSeed": 3,
    "maxRequests": 3
  },
  "callOptions": {
    "maxTotalChargeUsd": 0.25,
    "timeout": 300
  },
  "waitSecs": 30
}

After completion, use get-dataset-items with storages.datasets.default.id. If still running, poll get-actor-run using the returned runId. Check status rows and errors before treating an empty dataset as no matches.

Call from Python, JavaScript or REST

Python SDK 3 example · JavaScript SDK 2 example · curl + jq example. Each uses this same small input, reads APIFY_TOKEN from your environment, sets a five-minute run timeout and exports all dataset row types as JSON Lines. The $0.25 run ceiling is separate from the Actor input and may stop the sample early. Inspect the run and source status before treating results as complete. Installation and usage.

Pricing and limits

Current listed event prices in USD. Some Actors charge for successful source checks even when no output rows match. The event descriptions below define those differences.

EventUSD eachWhat is charged
query-parsed$0.002One successfully parsed seed or expanded query: $2 per 1,000 checks. Charged even when filters, exclusions, duplicates or monitoring leave zero rows. Failed/unrecognized responses and invalid input are not charged. A separate delivered-row fee applies. No start fee; compute included. No extra source account or API key. Work stops before a new check when the Apify run option maxTotalChargeUsd cannot cover that check plus one row.
suggestion$0.0001One delivered suggestion row: $0.1 per 1,000 rows. Row keys: seed, expanded_query, suggestion, position, country, language. Filtered, duplicate, excluded and unchanged rows are not charged. Successful source checks are separately billed at $0.002 each, including empty checks. No start fee; compute included. maxTotalChargeUsd is an Apify run option, not input.

Contracts for agents

Public contract checked 2026-11-11. Active build: 1.0.4. Refresh live details before a large or recurring run.