Google Ads Connector for AI Agents

Tools your ads management agent reaches for on Google Ads, scoped per user.

CALL ANY TOOL

List campaigns and ad groups, pull performance metrics, manage keywords, and update budgets.

googleads_ad_group_asset_link

Ad group asset link

Attach an existing asset to an ad group so it can serve with that ad group, for example a sitelink, callout or structured snippet. Ad-group links override campaign-level links for the same field type. Create the asset first with the asset creation tool, then link it here. The link is immutable: to change which asset or field type is used, remove the link and create a new one.

Parameters

Name

Type

Required

Description

ad_group

string

Required

Resource name of the ad group to attach the asset to, in the format customers/{customer_id}/adGroups/{ad_group_id}. To find it from an ad group name, run the search tool with: SELECT ad_group.resource_name, ad_group.name FROM ad_group WHERE ad_group.name = 'Your Ad Group'. It is also returned when an ad group is created.

asset

string

Required

Resource name of the asset to attach, in the format customers/{customer_id}/assets/{asset_id}. Returned when the asset is created. To find an existing one, run the search tool with: SELECT asset.resource_name, asset.name, asset.type FROM asset. The asset must already be of the type this link needs - sitelink, callout, structured snippet, call, price, promotion, mobile app and hotel callout assets have to exist in the account already, as the asset creation tool only makes text, image and YouTube video assets.

field_type

string

Required

How the asset is used by the ad group. Must match the asset's own type - a SitelinkAsset can only be linked as SITELINK, a CalloutAsset as CALLOUT, and so on.

customer_id

string

Optional

Google Ads customer account ID to operate on (digits only, no hyphens). Defaults to the Google Ads Customer ID entered when the account was connected; set it only to target a different account, e.g. a specific client account under a manager (MCC).

schema_version

string

Optional

Optional schema version to use for tool execution

tool_version

string

Optional

Optional tool version to use for execution

googleads_ad_group_bid_modifier

Ad group bid modifier

Create, update or remove an ad-group-level bid adjustment, so bids are raised or lowered for a segment such as a device type. A bid modifier of 1.5 bids 50% more, 0.5 bids 50% less, and 0 opts the segment out entirely. CREATE needs the ad group and the device; UPDATE and REMOVE need the bid modifier resource name. The device cannot be changed after creation - remove the modifier and create a new one instead.

Parameters

Name

Type

Required

Description

operation

string

Required

Which action to perform. CREATE adds a new bid modifier, UPDATE changes the multiplier on an existing one, REMOVE deletes it.

ad_group

string

Optional

Resource name of the ad group the adjustment applies to, in the format customers/{customer_id}/adGroups/{ad_group_id}. Required for CREATE. To find it, run the search tool with: SELECT ad_group.resource_name, ad_group.name FROM ad_group WHERE ad_group.name = 'Your Ad Group'.

bid_modifier

number

Optional

Bid multiplier applied when the criterion matches. Google requires it to be in the range 0.1 - 10.0, or exactly 0 to opt out of the device type entirely. 1.5 bids 50% more, 0.5 bids 50% less, 1.0 leaves bids unchanged. Required for CREATE and UPDATE; it is the only field UPDATE can change.

customer_id

string

Optional

device

string

Optional

Device type the adjustment applies to. Required for CREATE and immutable afterwards.

resource_name

string

Optional

Resource name of an existing bid modifier, in the format customers/{customer_id}/adGroupBidModifiers/{ad_group_id}~{criterion_id}. Required for UPDATE and REMOVE. To find it, run the search tool with: SELECT ad_group_bid_modifier.resource_name, ad_group_bid_modifier.bid_modifier, ad_group_bid_modifier.device.type FROM ad_group_bid_modifier WHERE ad_group.id = AD_GROUP_ID.

schema_version

string

Optional

Optional schema version to use for tool execution

tool_version

string

Optional

Optional tool version to use for execution

googleads_ad_group_create

Create ad group

googleads_ad_group_label_create

Create ad group label

googleads_ad_group_remove

Remove ad group

googleads_ad_group_update

Update ad group

googleads_ad_remove

Remove ad

googleads_ad_update

Update ad

googleads_asset_create

Create asset

googleads_bidding_strategy_create

Create bidding strategy

googleads_bidding_strategy_update

Update bidding strategy

googleads_budget_create

Create budget

googleads_budget_remove

Remove budget

googleads_budget_update

Update budget

googleads_campaign_asset_link

Campaign asset link

googleads_campaign_criterion_create

Create campaign criterion

googleads_campaign_criterion_remove

Remove campaign criterion

googleads_campaign_label_create

Create campaign label

googleads_campaign_remove

Remove campaign

googleads_campaign_update

Update campaign

googleads_conversion_action_create

Create conversion action

Create a conversion action to track valuable customer actions such as purchases, form submissions, phone calls, or app downloads. Conversion actions are used for Smart Bidding and performance measurement.

Parameters

Name

Type

Required

Description

category

string

Required

Category that best describes the conversion. PURCHASE=e-commerce transactions, SIGNUP=account registrations, LEAD=lead form submissions, CONTACT=contact page actions, PHONE_CALL_LEAD=phone call initiated, PAGE_VIEW=page views, OTHER=custom conversions.

name

string

Required

Name of the conversion action. Should clearly identify the customer action being tracked.

type

string

Required

Conversion type that determines how the conversion is tracked. WEBPAGE=tag on a webpage, CLICK_TO_CALL=phone call from an ad, GOOGLE_PLAY_DOWNLOAD=app download, UPLOAD_CLICKS=offline conversion imported from clicks, UPLOAD_CALLS=offline conversion imported from calls.

click_through_lookback_window_days

integer

Optional

Number of days after a click to attribute a conversion. Typical values are 7, 30, or 90 days.

counting_type

string

Optional

How conversions are counted. ONE_PER_CLICK counts at most one conversion per ad click. MANY_PER_CLICK counts all conversions per click (useful for purchases where a user might buy multiple times).

customer_id

string

Optional

schema_version

string

Optional

Optional schema version to use for tool execution

tool_version

string

Optional

Optional tool version to use for execution

value_settings_default_currency_code

string

Optional

Currency code for the default conversion value, e.g., USD, EUR, GBP.

value_settings_default_value

number

Optional

Default monetary value of each conversion. For example, 50.0 for a $50 conversion value.

view_through_lookback_window_days

integer

Optional

Number of days after an ad view (without a click) to attribute a conversion.

googleads_conversion_action_update

Update conversion action

googleads_customer_list_members_mutate

Customer list members mutate

Add or remove members of a Customer Match user list by uploading already-hashed contact details. The list must be a CRM-based (Customer Match) user list; a basic remarketing list cannot accept members. Each email or phone number is treated as one person, and Google caps a single upload at 10 people, so send large audiences in batches. Values must be normalised then SHA-256 hashed and hex encoded before they are passed in: trim whitespace, lowercase the whole value, and put phone numbers in E.164 form first. This service does not update the "Segment members" count shown in the Google Ads UI.

Parameters

Name

Type

Required

Description

operation

string

Required

Whether to add the supplied people to the list or remove them from it.

user_list

string

Required

Resource name of the Customer Match user list to modify, in the format customers/{customer_id}/userLists/{user_list_id}. It must be a CRM-based list; a basic remarketing list cannot hold uploaded members and will be rejected. To find eligible lists, run the search tool with: SELECT user_list.resource_name, user_list.name FROM user_list WHERE user_list.type = 'CRM_BASED'.

customer_id

string

Optional

hashed_emails

array

Optional

Email addresses of the people to add or remove, each normalised then SHA-256 hashed and hex encoded. Normalise by removing leading and trailing whitespace and lowercasing the whole address; additionally, for gmail.com and googlemail.com addresses only, strip every period from the part before the @ and drop the + together with everything after it, so Jane.Doe+Shop@gmail.com is hashed as janedoe@gmail.com. Skipping those Gmail rules produces a hash that silently fails to match anyone. Each entry counts as one person.

hashed_phone_numbers

array

Optional

Phone numbers of the people to add or remove, each converted to E.164 format with a leading + and the country code (for example +14155550123), then SHA-256 hashed and hex encoded. Each entry counts as one person.

schema_version

string

Optional

Optional schema version to use for tool execution

tool_version

string

Optional

Optional tool version to use for execution

googleads_customers_list

List customers

googleads_geo_target_constant_suggest

Geo target constant suggest

googleads_keyword_create

Create keyword

googleads_responsive_search_ad_create

Create responsive search ad

googleads_search

googleads_user_list_create

Create user list

googleads_user_list_update

Update user list

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your ads management agent can use Google Ads from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googleads"], toolNames: ["googleads_campaigns_list", "googleads_campaign_get", "googleads_ad_groups_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googleads"], toolNames: ["googleads_campaigns_list", "googleads_campaign_get", "googleads_ad_groups_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googleads"], toolNames: ["googleads_campaigns_list", "googleads_campaign_get", "googleads_ad_groups_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/googleads",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Google Ads.

Search & metrics

Copy the prompt

Copied

List all active campaigns.

Copy the prompt

Copied

Get performance metrics for [campaign] last 30 days.

Copy the prompt

Copied

Which ad groups have the highest CPC?

Copy the prompt

Copied

Show me all paused campaigns.

Action & updates

Copy the prompt

Copied

Update the daily budget for [campaign] to [$amount].

Copy the prompt

Copied

Pause campaign [name].

Copy the prompt

Copied

List keywords in [ad group].

Copy the prompt

Copied

Enable ad group [name] in [campaign].

Reporting & optimization

Copy the prompt

Copied

Which campaigns have conversion rate below 2%?

Copy the prompt

Copied

Compare CPC across all campaigns this month.

Copy the prompt

Copied

List campaigns with budget utilization above 90%.

Copy the prompt

Copied

Top 5 keywords by click volume.

SEE HOW AUTH WORKS

Users authorize Google Ads once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Google Ads

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Google Ads

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Google Ads

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Google Ads

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other ads management agents and MCP connectors. Working code, live demos, fork what fits.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Google Ads today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Google Ads as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Google Ads oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Google Ads?

Yes. Pass a tool name filter to listScopedTools so the ads management agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Google Ads.

What happens when a user revokes Google Ads access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent access accounts under a linked manager (MCC) account?

Only accounts the authorizing user has explicit access to. MCC child accounts require the user to have been granted account-level access before the agent can reach them.

What other MCP connectors does Scalekit support?

Scalekit runs the Mailchimp MCP server, Adzviser MCP server, and HubSpot MCP server on the same per-user auth, token vault, and audit trail. Browse 500+ connectors in the MCP connector directory.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit