Back to Browse

Google Trends Api MCP Server

Developer ToolsLow Risk10.0MCP RegistryRemote
Free

Server data from the Official MCP Registry

Google Trends search interest over time with growth metrics. Free key at trendsapi.ai

About

Google Trends search interest over time with growth metrics. Free key at trendsapi.ai

Remote endpoints: streamable-http: https://google-trends.api.trendsapi.ai/mcp

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (1 strong, 0 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.

Endpoint verified · Open access · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

env_vars

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Connect

Remote Plugin

No local installation needed. Your AI client connects to the remote endpoint directly.

Add this to your MCP configuration to connect:

{
  "mcpServers": {
    "ai-trendsapi-google-trends": {
      "url": "https://google-trends.api.trendsapi.ai/mcp"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Google Trends API

Python client for Google Trends data via the Trends API. Normalized 0-100 scores, history + growth, free tier. Not a scraper.

License: MIT PyPI Python npm

Key: trendsapi.ai/#get-key. HTTP contract and every source: trendsapi-ai/trendsapi.

Authentication

pip install google-trends-client
export TRENDSAPI_KEY=your_key

Python 3.9+. Same key as the HTTP API.

from google_trends_client import TrendsAPI

client = TrendsAPI()                    # TRENDSAPI_KEY
# client = TrendsAPI(api_key="YOUR_KEY")

Keyword helpers default to source: "google search". Pass source= to hit any other platform with the same client. Official full client (every source, no preset): trendsapi.

Methods

MethodREST modeReturns
get_time_series(keyword, source=, data_mode=)get_time_serieslist[TrendsDataPoint]
get_growth(keyword, percent_growth=, source=, data_mode=)get_growthGetGrowthResponse
get_live(limit=, offset=, category=)get_top_trendsGetTopTrendsResponse
get_top_trends(type=, ...)get_top_trendsGetTopTrendsResponse

source is lowercase (google search). type is exact (Google Trends). Mixing them is a 400.

from google_trends_client import TrendsAPI

client = TrendsAPI()                    # TRENDSAPI_KEY
# client = TrendsAPI(api_key="YOUR_KEY")

series = client.get_time_series("heat pump")
print(series[-1].date, series[-1].value)

growth = client.get_growth("heat pump", percent_growth=["3M", "12M"])
print(growth.results[0].growth, growth.results[0].direction)

hot = client.get_live(limit=10)
print(hot.data)                         # [[1, "..."], ...]

get_time_series

points = client.get_time_series("heat pump")

Each point:

FieldAlwaysMeaning
dateyesYYYY-MM-DD
valueyes0-100 index for this series
keywordyesEcho
volumenoAbsolute volume when available
source or datatypenoPipeline label

Python returns list[TrendsDataPoint]. Use .date and .value, not ["date"]. JS returns the same fields as object properties.

get_growth

g = client.get_growth("heat pump", percent_growth=["12M", "3M", "YTD"])
print(g.results[0].growth, g.results[0].direction)

percent_growth default: ["12M"]. Presets: 7D 14D 30D 1M 2M 3M 6M 9M 12M/1Y 18M 24M/2Y 36M/3Y 48M 60M/5Y MTD QTD YTD. Custom: {"name": "Launch", "recent": "2024-06-01", "baseline": "2024-01-01"}.

FieldMeaning
search_termKeyword
data_sourceSource
resultsOne object per window (period, growth, direction, dates, values)
metadataCounts / success flag

Several windows still count as one request. Python: growth.results[0].growth. JS: growth.results[0].growth.

get_live

hot = client.get_live(limit=10)
FieldMeaning
as_of_tsSnapshot time
typeFeed name
limit, offset, countPagination
data[rank, label] rows

Python: hot.data. JS: hot.data. Optional offset= and category= (Amazon Best Sellers by Category, Top Websites only).

Async

import asyncio
from google_trends_client import AsyncTrendsAPI

async def main():
    c = AsyncTrendsAPI()
    return await asyncio.gather(
        c.get_time_series("heat pump"),
    )

asyncio.run(main())

Each 200 is one billed request.

Pandas

from dataclasses import asdict
import pandas as pd
from google_trends_client import TrendsAPI

df = pd.DataFrame(asdict(p) for p in TrendsAPI().get_time_series("heat pump"))
df["date"] = pd.to_datetime(df["date"])
print(df.set_index("date")["value"].resample("ME").mean().tail())

JavaScript / TypeScript

npm install google-trends-js

Node 18+, Deno, Bun, Workers. Same API key. Field tables above apply.

Also published as google-trends-node, google-trends-client. Same client, different package name.

Methods

MethodREST modeReturns
getTimeSeries(keyword, { source, data_mode })get_time_seriesweekly points
getGrowth(keyword, { percent_growth, source, data_mode })get_growthgrowth object
getLive({ limit, offset, category })get_top_trendslive feed
getTopTrends({ type, ... })get_top_trendslive feed
import { TrendsAPI } from "google-trends-js";

const client = new TrendsAPI({ apiKey: process.env.TRENDSAPI_KEY! });
const series = await client.getTimeSeries("heat pump");
console.log(series.at(-1)?.date, series.at(-1)?.value);

const growth = await client.getGrowth("heat pump", {
  percent_growth: ["3M", "12M"],
});
console.log(growth.results[0].growth, growth.results[0].direction);

const live = await client.getLive({ limit: 10 });
console.log(live.data);                 // [[1, "..."], ...]

Call (curl)

FieldValue
EndpointPOST https://api.trendsapi.ai/api
AuthAuthorization: Bearer $TRENDSAPI_KEY
Historysource: google search with get_time_series or get_growth
KeywordAny phrase, e.g. heat pump
Live typeGoogle Trends
curl -sS -X POST https://api.trendsapi.ai/api \
  -H "Authorization: Bearer $TRENDSAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"mode":"get_time_series","source":"google search","keyword":"heat pump"}'

Source notes

  • Related sources (same endpoint, different source): google images, google news, google shopping.
  • value is 0-100 for this term on Google web search, not Ads impressions.

Errors

HTTPClient
200Parsed payload. Python dataclasses / JS typed objects
400Raises. Fix source or type spelling
401Raises. Check TRENDSAPI_KEY
404Raises. No series for that keyword. Do not retry
429Raises. Quota
5xxClient retries, then raises

The HTTP body field is a JSON string. SDKs decode it. Raw curl must parse body a second time.

Site: https://trendsapi.ai/trends/google-trends.

License

MIT. See LICENSE.

Reviews

No reviews yet

Be the first to review this server!