Start free

Platforms MCP server

MCP server · 3 tools · 2 endpoints

Google Trends MCP server

Interest over time and rising related queries, so an agent can tell growing from fading before you plan content.

Get a free key Connect in a minute

100 credits on signup · No card · Sign in with OAuth or paste a key

scrapersocial-google_trends mcp.scrapersocial.com/google_trendsconnected
you

Is interest in <topic> growing or declining? Pull the interest-over-time report and describe the curve.

agent
calls get_trending 3 credits / query
{ "query": "<keywords>" }
server
returns
queries [{ … }] · one per query
Shape only. Keys follow the tool's summary; a real call returns the full record. 1 call · 3 credits

Connect

One URL. Your client already knows what to do with it.

The first call opens a sign-in. New accounts get 100 credits, no card. Every client below shares one account and one balance.

Get a free key
server url https://mcp.scrapersocial.com/google_trends
claude.aiOAuth

Settings → Connectors → Add custom connector, then paste the server URL.

mcp.scrapersocial.com/google_trends

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

$ claude mcp add --transport http scrapersocial-google_trends https://mcp.scrapersocial.com/google_trends

Approve the sign-in prompt on first use.

Cursorone click

Installs the server and opens the MCP panel.

Add to Cursor
or paste the JSON into .cursor/mcp.json
{ "mcpServers": { "scrapersocial-google_trends": { "url": "https://mcp.scrapersocial.com/google_trends", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Other clients · VS Code, Windsurf, Gemini CLI, anything that speaks MCP
VS Codeone click or JSON
Add to VS Codeor run MCP: Add Server, choose HTTP and use:
{ "name": "scrapersocial-google_trends", "type": "http", "url": "https://mcp.scrapersocial.com/google_trends" }
Windsurf~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "scrapersocial-google_trends": { "serverUrl": "https://mcp.scrapersocial.com/google_trends", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Gemini CLI~/.gemini/settings.json
{ "mcpServers": { "scrapersocial-google_trends": { "httpUrl": "https://mcp.scrapersocial.com/google_trends", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Any clientStreamable HTTP · OAuth 2.1 or Bearer
$ npx add-mcp https://mcp.scrapersocial.com/google_trends

One account and one balance across every client and the every-platform hub at mcp.scrapersocial.com.

What it does

What your agent can do with Google Trends

Is interest in a topic growing or fading, and what are people starting to search for alongside it. Those are the two questions Google Trends answers, and the two endpoints served from https://mcp.scrapersocial.com/google_trends map to them exactly.

get_trending is the capability tool. Pass a seed term and it returns the rising related queries around it, 3 credits per query returned. It calls /v1/google_trends/rising underneath. The second endpoint, /v1/google_trends/explore, returns the interest-over-time report for a term as a single record for 6 credits. It isn’t wrapped by a tool, so the agent reaches it through call_endpoint after list_endpoints, which is free, has shown it the path. Both take a plain query string.

What you get is relative interest on Google’s 0 to 100 index, not search volume. No endpoint here converts it into a volume estimate, and any agent that presents it as one is inferring rather than reporting; tell your model so in its system prompt. Trends is a research product rather than a social network. It belongs on ScraperSocial anyway, as public web data, because keyword research, trend spotting and content planning all begin here.

Costs are higher than on most ScraperSocial spokes because each report is heavier to produce, so this is a page to read before looping a keyword list.

Four jobs it finishes on its own

01

Content calendar planning

Give get_trending a category keyword and let the model turn the rising queries into article ideas ranked by momentum. Twenty rising queries is 60 credits, which is a month of topic research for a small blog.

02

Checking a trend before committing

Before a campaign or a product bet, pull /v1/google_trends/explore for the term and have the agent describe the curve: seasonal, climbing, or past its peak. One call, 6 credits, and you avoid guessing.

03

Comparing two terms

Run explore for each candidate name or feature and compare the shapes side by side. Twelve credits settles arguments that otherwise run for a whole meeting.

04

Spotting what to cover next

Rising related queries are an early signal of where a conversation is heading. A weekly run on a few seed terms costs well under 200 credits and feeds a newsletter or a product roadmap.

Limits · read before you connect

What this does not do

Written by a person, not generated. If something here is wrong, tell us.

Relative interest only. The index runs from 0 to 100 against the term’s own peak, so a value of 50 says nothing about how many searches happened, and there is no absolute volume anywhere in the catalogue. explore returns one report per call at 6 credits and does not paginate. rising is the paginated one: twenty queries on a default page, fifty at the most, 3 credits apiece, and a cursor in the meta block for anything beyond. A cached report answers repeat calls; the fresh flag forces a new pull for the same 6 credits. Two endpoints is the whole surface: no regional breakdowns, no categories and no comparison endpoint, so compare by making two calls. Even an empty result bills 1 credit.

Tools

3 tools, same names as the every-platform hub

One does one Google Trends thing each. The last two reach all 2 endpoints by path, so nothing in the catalog is out of an agent's reach.

Full credit table →

Get what is trending

get_trending

What is currently trending or rising on a platform.

3 credits / query
Reaches the other 1 endpoint

List every Google Trends endpoint

list_endpoints

Browse every Google Trends endpoint, its input and its credit cost. Free, and calls nothing upstream.

free

Call any Google Trends endpoint by path

call_endpoint

Run any Google Trends endpoint by its path, so nothing Google Trends offers is out of reach of an agent.

endpoint's own cost

Pricing

100 free credits is 33 trending results.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Calls cost between 3 and 6 credits on Google Trends.

33 trending resultsget_trending · 3 each
Get a free key 100 credits on signup · $5 for 1,000 · full credit table

Prompts

Things to ask once it is connected

Copy one, swap the placeholder, paste it into your client.

Is interest in <topic> growing or declining? Pull the interest-over-time report and describe the curve.

What related searches are rising around <keyword>? Give me the top 20 as content ideas.

Compare search interest for <term A> and <term B> and tell me which one is gaining.

Run interest over time for <product name> and flag any seasonal pattern.

Find rising queries around <industry> and group them into themes.

Questions

Before you connect

How much does a Trends call cost? #

Rising queries are 3 credits each, so a default page of 20 is 60 credits. An explore report is a flat 6 credits. With 100 free credits you can run one report and one page of rising queries before deciding whether to buy more.

Does this give me search volume numbers? #

No. Google Trends publishes relative interest indexed to 100, and this server returns exactly that. Any absolute number would be an inference the model made up.

Why isn't there a tool for explore? #

The capability tools wrap roles shared across platforms, and an interest-over-time report is specific to Trends. list_endpoints lists /v1/google_trends/explore and call_endpoint runs it; the cost and output are identical.

Can I limit results to one country or time range? #

There are no region or date parameters in the catalogue. Fold location into the query if you must, and treat the result as a general view rather than a filtered one.

Is this an official Google Trends API? #

No. Google neither runs nor endorses ScraperSocial, which is independent and reads publicly available Trends data.