Agentic Platform
Documentation API reference Tools Skills

Tools

Google AI Mode

google_ai_mode MCP Google Web search

Query Google AI Mode to get AI-generated search results and insights.

Retrieve AI-powered search results from Google AI Mode. Get comprehensive AI-generated answers, featured snippets, and search insights for any query.

Playground

Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.

POST
item
query required The search query to analyze
config
location_id Location ID (optional)
location_request Location request (ex: Paris, FR), will translate to location ID
country_code ISO3166 country code (ex: GB)
lang_code BCP47 language code (ex: "en", "en-GB")
device Device to use for search (optional - defaults to mobile)

Billing

Fixed cost per query requested, plus one AI Mode answer per query. Called synchronously it uses AI Mode results (live); submitted as a background batch it uses AI Mode results (async), at roughly a third of the price, and collecting the finished batch is free.

These usage SKUs can be charged on a call.

SKU Credits Description
Tool call 1 per request Charged once per successful item, on top of any usage below.
AI Mode results (async) 12 per 10 query The same AI Mode answer, submitted as a background batch.
AI Mode results (live) 4 per query One AI Mode answer for one query, fetched while you wait.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
query string required

The search query to analyze

max length 700

Example
{
  "query": "string"
}

Configuration

object
Properties
location_id integer | null

Location ID (optional)

Default: null

location_request string | null

Location request (ex: Paris, FR), will translate to location ID

Default: null

country_code string | null

ISO3166 country code (ex: GB)

Default: null

lang_code string | null

BCP47 language code (ex: "en", "en-GB")

Default: null

device string

Device to use for search (optional - defaults to mobile)

Values: mobile desktop

Default: "mobile"

Example
{
  "location_id": null,
  "location_request": null,
  "country_code": null,
  "lang_code": null,
  "device": "mobile"
}

Response

object
Properties
query string required

The original search query

location_name string required

The location used for the search, if any

results GoogleAiModeResults required

The AI-generated search results

Type: GoogleAiModeResults

Example
{
  "query": "string",
  "location_name": "string",
  "results": {
    "type": "ai_mode",
    "rank_group": 0,
    "rank_absolute": 0,
    "markdown": "string",
    "items": null,
    "model": null
  }
}

Type Definitions

5 types

These are the available sub-object types that can be used in the properties above.

GooglAiOverviewReference object
#
type string required
source string required
domain string required
url string required
title string required
text string | null

Default: null

GoogleAiModeResults object
#
type string

Default: "ai_mode"

rank_group integer required
rank_absolute integer required
markdown string | null required
items GoogleAiOverviewElement

Items: GoogleAiOverviewElement

Default: null

model string | null

Name / version of the model used

Default: null

GoogleAiOverviewElement object
#
type string required
title string | null

Default: null

text string | null

Default: null

markdown string | null

Default: null

links GoogleAiOverviewLinkElement

Items: GoogleAiOverviewLinkElement

Default: null

images GoogleAiOverviewImageElement

Items: GoogleAiOverviewImageElement

Default: null

references GooglAiOverviewReference

Items: GooglAiOverviewReference

Default: null

GoogleAiOverviewImageElement object
#
type string required
alt string | null

Default: null

url string | null

Default: null

image_url string required
GoogleAiOverviewLinkElement object
#
type string required
title string required
description string | null

Default: null

url string | null

Default: null

domain string | null

Default: null

Endpoints

POST http://agents.botify.com/{organization}/{project}/google_ai_mode/process
POST http://agents.botify.com/{organization}/{project}/google_ai_mode/batch_process
POST http://agents.botify.com/{organization}/{project}/google_ai_mode/async_process
POST http://agents.botify.com/{organization}/{project}/google_ai_mode/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/google_ai_mode/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "query": "<query>"
  }
}'

Over MCP

This tool is exposed as the MCP tool google_ai_mode. An MCP client passes organization, project and item as tool arguments. Set up MCP →

Raw metadata