Serper connector for AI agents

Tools your search agent reaches for on Serper, scoped per user.

CALL ANY TOOL

13 tools for web search through Serper: search Google web, news, images, videos, maps, places, shopping, Scholar, and Patents, get autocomplete suggestions, list place reviews, and scrape webpages.

serper_autocomplete

Autocomplete

Get Google's autocomplete suggestions for a partial query through Serper. Returns suggestions, each with the suggested query as value. Use this to expand or refine a search query, or for keyword research. Use serper_search to run the search itself.

Parameters

Name

Type

Required

Description

string

Required

The partial query to complete, as you would type it into Google. Google search operators such as site:, filetype: and quotes work. Example: how to build your own

string

Optional

Two-letter country code (Google's gl parameter, lowercase) that sets which country's Google results to return. Serper uses us when omitted. Example: gb

string

Optional

Google interface language code (Google's hl parameter) for the results, usually a two-letter language code, or language-region for a few languages such as zh-cn. Serper uses en when omitted. Example: fr

location

string

Optional

Place to run the search from, as a Google location name (city, region or country, comma-separated, most specific first). Results are localized as if searched from there. Example: Austin, Texas, United States

serper_list_place_reviews

List place reviews

serper_scrape_webpage

Scrape webpage

serper_search

serper_search_by_image

Search by image

serper_search_images

Search images

serper_search_maps

Search maps

serper_search_news

Search news

serper_search_patents

Search patents

serper_search_places

Search places

serper_search_scholar

Search scholar

serper_search_shopping

Search shopping

serper_search_videos

Search videos

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);

// Serper tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["serper"], toolNames: [
    "serper_search",
    "serper_search_news",
    "serper_scrape_webpage"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find this week's news on AI agent security and scrape the top article" }] });

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: ["serper"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find this week's news on AI agent security and scrape the top article" }],
  tools,
});

// Execute the tool call with the user's vaulted Serper API key
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: ["serper"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find this week's news on AI agent security and scrape the top article" }],
  tools,
});

// Tool call runs with the user's vaulted Serper API key
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: ["serper"] }, pageSize: 100,
});

const agent = new Agent({
  name: "search_agent",
  model: "gemini-2.5-pro",
  instruction: "Serper tools scoped to this user",
  tools,
});

await agent.run("Find this week's news on AI agent security and scrape the top article");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Serper tool. Click to copy, paste into your agent, done.

Web and news

Copy the prompt

Copied

Search Google for this vendor's pricing page.

Copy the prompt

Copied

Find news coverage of our competitor from the past week.

Copy the prompt

Copied

Get autocomplete suggestions for 'mcp server'.

Local and shopping

Copy the prompt

Copied

Find coffee shops near this address with their ratings.

Copy the prompt

Copied

List the latest Google reviews for this place.

Copy the prompt

Copied

Compare prices for this laptop on Google Shopping.

Research

Copy the prompt

Copied

Search Google Scholar for papers on agent tool calling.

Copy the prompt

Copied

Find patents on wireless charging assigned to this company.

Copy the prompt

Copied

Scrape this public webpage and return it as markdown.

SEE HOW AUTH WORKS

Each user connects their own Serper API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Serper

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

Serper

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

Serper

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

Serper

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 search and analytics 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

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Serper API key looks fine in a demo. In production every search looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Serper 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

Does the agent access Serper as the user or through a shared key?

As the user. Each user connects their own Serper API key once, and Scalekit sends it with every call. Audit logs attribute every search and scrape to that user, not a shared service account.

Where is the Serper API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Serper?

Yes. All 13 Serper tools are read-only: they search Google results and fetch public webpages but change nothing. Filter by tool name in listScopedTools to narrow it further, for example to serper_search and serper_search_news. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Serper 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.

Which Google results can the agent search through Serper?

Web, News, Images, Videos, Maps, local places, Shopping, Scholar, and Patents, plus Google Lens reverse image search and autocomplete suggestions. serper_list_place_reviews reads a place's Google reviews, and serper_scrape_webpage returns a public page's text, optionally as markdown.