Google Search Console connector for AI agents

Tools your agent reaches for on Google Search Console, scoped per user.

CALL ANY TOOL

Query search analytics, submit and inspect sitemaps, and run URL inspection against the verified sites the signed-in user owns.

googlesearchconsole_add_site

Add site

Adds a site (property) to the set of the authorized user's sites in Search Console. The site is added with the caller as owner if verification is already established, otherwise it is added as an unverified site pending verification. Requires the webmasters (full-access) scope. NOTE: this API requires siteUrl as a single percent-encoded path segment — Scalekit does not auto-encode path values, so you must pass siteUrl already percent-encoded (replace ':' with %3A and every '/' with %2F). Returns an empty response on success.

Parameters

Name

Type

Required

Description

siteUrl

string

Required

Required. The percent-encoded URL of the site to add, e.g. 'https://www.example.com/' percent-encoded to 'https%3A%2F%2Fwww.example.com%2F', or 'sc-domain:example.com' percent-encoded to 'sc-domain%3Aexample.com'.

googlesearchconsole_delete_site

Delete site

googlesearchconsole_delete_sitemap

Delete sitemap

googlesearchconsole_get_site

Get site

googlesearchconsole_get_sitemap

Get sitemap

googlesearchconsole_inspect_url

Inspect url

googlesearchconsole_list_sitemaps

List sitemaps

googlesearchconsole_list_sites

List sites

googlesearchconsole_query_search_analytics

Query search analytics

Queries Google Search performance data (clicks, impressions, CTR, position) for a site, filtered and grouped by the dimensions you define. Returns zero or more rows grouped by the row keys you specify via `dimensions`. You must supply a date range (startDate/endDate) of one or more days. When `DATE` is one of the group-by dimensions, days without data are omitted from the results. Requires the webmasters or webmasters.readonly scope. NOTE: siteUrl must be a single percent-encoded path segment — Scalekit does not auto-encode path values, so pass siteUrl already percent-encoded (replace ':' with %3A and every '/' with %2F).

Parameters

Name

Type

Required

Description

endDate

string

Required

Required. End date of the requested date range, in YYYY-MM-DD format, in PST time (UTC-8:00). Must be >= startDate. Inclusive.

siteUrl

string

Required

Required. The percent-encoded URI of the property as defined in Search Console. Get the raw value from the List Sites tool, then percent-encode it: 'https://www.example.com/' becomes 'https%3A%2F%2Fwww.example.com%2F'; 'sc-domain:example.com' becomes 'sc-domain%3Aexample.com'.

startDate

string

Required

Required. Start date of the requested date range, in YYYY-MM-DD format, in PST time (UTC-8:00). Must be <= endDate. Inclusive.

aggregationType

string

Optional

Optional; default AUTO. How data is aggregated — AUTO, BY_PROPERTY, or BY_PAGE (BY_NEWS_SHOWCASE_PANEL for News Showcase reporting). If you filter or group by PAGE, you must use AUTO. An invalid combination returns an API error rather than silently changing your request.

dataState

string

Optional

Optional. The data freshness to include — FINAL (final data only, the default behavior when omitted), ALL (final + partial/fresh data), or HOURLY_ALL (hourly partial + full data; required when dimensions includes HOUR).

dimensionFilterGroups

array

Optional

Optional. Zero or more filter groups to apply to the dimension values, e.g. 'query contains "buy"'. You can filter by a dimension without grouping by it. All filter groups are AND'ed together; filters within a group follow the group's groupType.

dimensions

array

Optional

Optional. Zero or more dimensions to group results by — DATE, QUERY, PAGE, COUNTRY, DEVICE, SEARCH_APPEARANCE, or HOUR (HOUR requires dataState=HOURLY_ALL and data is only available for the last 10 days). Results are grouped in the order supplied.

rowLimit

integer

Optional

Optional; default 1000. The maximum number of rows to return. Must be from 1 to 25000 (inclusive).

startRow

integer

Optional

Optional; default 0. Zero-based index of the first row to return, for paging through results beyond rowLimit.

type

string

Optional

Optional; default WEB. The Search type to report on — WEB, IMAGE, VIDEO, NEWS, DISCOVER, or GOOGLE_NEWS.

googlesearchconsole_submit_sitemap

Submit sitemap

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Google Search Console tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlesearchconsole"], toolNames: [
    "googlesearchconsole_add_site",
    "googlesearchconsole_delete_site",
    "googlesearchconsole_delete_sitemap"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Is the Salesforce sync healthy?" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlesearchconsole"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which data sources are connected?" }],
  tools,
});

// Execute the tool call with the user's vaulted Google Search Console credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlesearchconsole"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull open Zendesk tickets created this week." }],
  tools,
});

// Tool call runs with the user's vaulted Google Search Console credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlesearchconsole"] }, pageSize: 100,
});

const agent = new Agent({
  name: "googlesearchconsole_agent",
  model: "gemini-2.5-pro",
  instruction: "Work with Google Search Console for the signed-in user.",
  tools,
});

await agent.run("What auth does the Shopify connector need?");

Try these prompts

Paste any prompt into your agent to get started.

Search performance

Copy the prompt

Copied

Which queries lost the most clicks in the last 28 days?

Copy the prompt

Copied

Show me pages that rank between position 5 and 15.

Copy the prompt

Copied

Compare mobile and desktop click-through rate this month.

Indexing

Copy the prompt

Copied

Inspect this URL and tell me if it is indexed.

Copy the prompt

Copied

List the sitemaps submitted for this property.

Copy the prompt

Copied

Submit the updated sitemap and confirm it was accepted.

Site management

Copy the prompt

Copied

List every site I have verified.

Copy the prompt

Copied

Get the details for this property.

Copy the prompt

Copied

Delete the stale sitemap from last year.

SEE HOW AUTH WORKS

Your users connect Search Console once. Their credentials stay vaulted, every call is scope checked, and every inspection is logged.

Authorize

Your user connects

Google Search Console

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 Search Console

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 Search Console

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 Search Console

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

See the same per-user auth pattern across other connectors.

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.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

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

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Google Search Console token looks fine in a demo. In production every action looks like one service account, and you cannot tell who wired a source or ran a query. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Google Search Console today. Ten connectors 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

Can the agent see properties the user has not verified?

No. Search Console evaluates the user's own verification status at request time, so the agent's reach matches the person who triggered it.

Is URL inspection rate limited?

Google rate limits inspection per property. Scalekit surfaces the API error rather than silently retrying, so your agent can back off deliberately.

Can I allow reporting but block sitemap submission?

Yes. Scope the connection to the query and list tools. Submit and delete stay unavailable, enforced before the call.

How many tools does this connector expose?

10, covering sites, sitemaps, URL inspection, and search analytics.

How are credentials isolated between customers?

Per tenant and per user in an encrypted vault, resolved at request time and never placed in LLM context.

On this page

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