# Google Trends (pypi · gtrends-mcp-full)

Google Trends: Trending Now, interest over time, regions, related searches. No API key.

- Trust score: 62/100 (medium)
- Change this week: −3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `gtrends-mcp-full`: 62/100 (this document), [markdown](https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full.md), [page](https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full)

## Channel facts

- Registry: `pypi`
- Package: `gtrends-mcp-full`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 33 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 15 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4876 tokens (~143/item across 34 items; 32 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 34 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Google Trends MCP server?

Google Trends runs locally as a PyPI package, launched with uvx gtrends-mcp-full. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mamrrez-gtrends-mcp-full -- uvx gtrends-mcp-full
```

### Cursor

```json
{
  "mcpServers": {
    "mamrrez-gtrends-mcp-full": {
      "command": "uvx",
      "args": [
        "gtrends-mcp-full"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mamrrez-gtrends-mcp-full": {
      "command": "uvx",
      "args": [
        "gtrends-mcp-full"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mamrrez-gtrends-mcp-full -- uvx gtrends-mcp-full
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mamrrez-gtrends-mcp-full": {
      "type": "local",
      "command": [
        "uvx",
        "gtrends-mcp-full"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mamrrez-gtrends-mcp-full --command uvx --arg gtrends-mcp-full
```

### Hermes

```yaml
mcp_servers:
  mamrrez-gtrends-mcp-full:
    command: "uvx"
    args: ["gtrends-mcp-full"]
```

### Netclaw

```json
{
  "McpServers": {
    "mamrrez-gtrends-mcp-full": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "gtrends-mcp-full"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mamrrez-gtrends-mcp-full -t stdio -c uvx -a gtrends-mcp-full
```

### Other

```json
{
  "mcpServers": {
    "mamrrez-gtrends-mcp-full": {
      "command": "uvx",
      "args": [
        "gtrends-mcp-full"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-16 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 60, +5)

- [functional improvement] Stability: unverified → 0.37

### 2026-10-12 (score 55, −10)

- [security regression] Malware scan: pass → unverified
- [security improvement] Source repository: unverified → pass

### 2026-10-08 (score 65, −5)

- [security regression] Provenance: pass → unverified

### 2026-10-03 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-02 (score 55)

First indexed and scored.

## MCP tools (32)

### `get_capabilities` (~32 tokens)

Version, settings, session and cache state, saved history and the list of tools. Call this first when unsure.

Output parameters:

- `result` (string)

### `check_endpoints` (~92 tokens)

Ask each Google Trends endpoint one small question and report which ones answer.

Google Trends has no public API; this server uses the endpoints of the Trends website,
which can change without notice. Run this when a tool fails unexpectedly: it separates
"Google is rate-limiting me" from "this endpoint changed" from "the network is down".
Sends about 12 requests and never answers from the cache.

Output parameters:

- `result` (string)

### `find_location` (~132 tokens)

Find the location code (geo) for a country, region, state or metro area by name.

query: part of a name ("tehran", "calif", "bavaria") or a code ("IR").
inside: a code whose sub-locations to list instead ("IR" → its provinces, "US-CA" → its metro areas).
Codes look like IR, US, US-CA, US-CA-807. Every other tool takes them as `geo`; blank means worldwide.

Input parameters:

- `inside` (string)
- `limit` (integer)
- `query` (string)

Output parameters:

- `result` (string)

### `find_category` (~110 tokens)

Find the id of a Google Trends category ("Autos & Vehicles" = 47) to narrow a term to one meaning.

A category limits a search term to searches Google files under that subject — "jaguar" in
Autos & Vehicles is the car, in Pets & Animals the cat. Pass the id as `category` to the explore tools.
With no keyword at all, a category id shows interest in the whole subject.

Input parameters:

- `limit` (integer)
- `query` (string, required)

Output parameters:

- `result` (string)

### `find_topic` (~105 tokens)

Find the Google Trends *topics* for a piece of text and the ids that select them.

A search term ("tesla") counts only searches containing that exact wording, in one language.
A topic ("Tesla — Automotive company", id /m/0dr90d) counts every search about the thing,
in any language and spelling, and leaves out other meanings (the band, the inventor).
Pass a topic id wherever a keyword is expected.

Input parameters:

- `text` (string, required)

Output parameters:

- `result` (string)

### `clear_cache` (~107 tokens)

Delete saved answers so the next call asks Google again.

what: "expired" (default — only answers too old to be used even as a fallback), "all", or one kind:
trending, timeseries, regions, related, explore.
reset_session: also forget the stored session cookie and any back-off, for a clean start after a block.
Saved Trending Now history and the watchlist are never touched.

Input parameters:

- `reset_session` (boolean)
- `what` (string)

Output parameters:

- `result` (string)

### `trending_now` (~240 tokens)

What people are searching right now: the full Trending Now list for a country or region.

Each trend has its search volume, growth, start time, whether it is still active, its
category and the other queries people type for the same story.

geo: country or region code (US, GB, DE, IR, US-CA). Blank = the default location, else US.
hours: look-back window — 4, 24, 48 or 168 (any value 1-191).
category: filter by name, e.g. "sports", "technology", "business" (see the header of the result).
status: "active" (still trending), "ended" or "all".
sort_by: "volume", "growth" or "recent".
contains: keep trends whose title or queries contain this text, as whole words.

Input parameters:

- `category` (string)
- `contains` (string)
- `geo` (string)
- `hours` (integer)
- `limit` (integer)
- `min_volume` (integer)
- `sort_by` (string)
- `status` (string)

Output parameters:

- `result` (string)

### `trend_details` (~117 tokens)

Everything about one current trend: every query in it, the news behind it, and its hour-by-hour curve.

trend: the trend's title, or any words it contains.
geo: country or region code; blank = the default location, else US.
with_chart: also fetch the last 7 days of hourly interest for the title (two more requests).

Input parameters:

- `geo` (string)
- `hours` (integer)
- `news` (integer)
- `trend` (string, required)
- `with_chart` (boolean)

Output parameters:

- `result` (string)

### `trending_feed` (~96 tokens)

The top daily search trends with the news stories behind each — Google's public trending feed.

Lighter than trending_now (about 10-20 trends, one request) and it carries headlines and
links, which makes it the quickest answer to "what is in the news in <country> today".
geo: country code; blank = the default location, else US.

Input parameters:

- `geo` (string)
- `limit` (integer)

Output parameters:

- `result` (string)

### `trending_across_countries` (~135 tokens)

Trends that are live in several countries at once — the stories that travel.

Pulls Trending Now for each country and groups trends that are the same search (the same
title, or one country's title appearing among another's queries).

geos: comma-separated country codes, up to 12. Blank = US, GB, CA, AU, IN, DE, FR, BR.
min_countries: only show trends found in at least this many of them.

Input parameters:

- `geos` (string)
- `hours` (integer)
- `limit` (integer)
- `min_countries` (integer)

Output parameters:

- `result` (string)

### `match_trends` (~125 tokens)

Which current trends touch your subjects — for newsjacking and timely content.

terms: comma-separated words or phrases that define your niche (brands, products, people,
subjects). A trend matches when its title or any query inside it contains one of them as
whole words, in any letter case: "ai" finds «ai news», not «rain».
geo: country or region code; blank = the default location, else US.

Input parameters:

- `geo` (string)
- `hours` (integer)
- `limit` (integer)
- `terms` (string, required)

Output parameters:

- `result` (string)

### `interest_over_time` (~299 tokens)

Search interest over time for up to 5 terms on one shared scale — the main Google Trends chart.

keywords: comma-separated terms or topic ids (find_topic). Operators work inside a term:
\`a + b` either wording, `a -b` excluding b, `"a b"` exact phrase. Blank with a `category`
measures the whole category.
timeframe: 1h, 4h, 1d, 7d, 1m, 3m, 12m, 5y, all; any 6m / 2y / 45d; a year 2024; a month
2024-03; or explicit dates "2024-01-01 2024-12-31". Short ranges come back by the minute
or hour, up to ~9 months daily, up to 5 years weekly, longer monthly.
geo: location code (find_location); blank = default location, usually worldwide.
category: category id (find_category) to pin down an ambiguous term.
property: web, youtube, news, images or shopping.
points: rows of data to return (longer series are averaged down); 0 = summary only.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keywords` (string)
- `points` (integer)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `interest_by_region` (~203 tokens)

Where a term is most popular: countries, regions, cities or metro areas ranked by interest.

With one term, each place gets 0-100 relative to the strongest place — interest as a share
of that place's own searches, so a small region can outrank a large one. With 2-5 terms,
each place shows how its interest splits between them (percentages), i.e. who wins where.

geo: blank = worldwide (ranks countries); a country ranks its regions; a region its cities.
resolution: auto, country, region, city, or dma (US metro areas).
include_low_volume: also list places with little search volume.

Input parameters:

- `category` (integer)
- `geo` (string)
- `include_low_volume` (boolean)
- `keywords` (string, required)
- `limit` (integer)
- `property` (string)
- `resolution` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `related_queries` (~135 tokens)

What else people who search a term also search: the top related queries and the rising ones.

Rising = the largest growth against the previous period; "Breakout" means more than +5000%,
usually a query that barely existed before. Top = the most searched, 100 being the most common.
keyword: one term or topic id. timeframe, geo, category, property: as in interest_over_time.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `limit` (integer)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `related_topics` (~127 tokens)

The topics (people, brands, things) searched alongside a term, top and rising, with their topic ids.

Google withholds this list from anonymous sessions: without a signed-in cookie
(GTRENDS_COOKIE or GTRENDS_COOKIES_FILE) it usually comes back empty, and this tool says so
rather than pretending there are none. related_queries works either way.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `limit` (integer)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `compare_periods` (~163 tokens)

One term in two time ranges on the same scale: this year against last year, this quarter against the one before.

period: the range to look at (3m, 12m, 2026, 2026-03, or explicit dates; not hours).
against: "year_before" (same dates a year earlier), "previous" (the range just before), or another range.
The two curves are aligned by position, so day 10 of one sits beside day 10 of the other.

Input parameters:

- `against` (string)
- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `period` (string)
- `points` (integer)
- `property` (string)

Output parameters:

- `result` (string)

### `compare_locations` (~134 tokens)

One term in up to 5 countries or regions side by side: where it matters more, and whether the curves move together.

geos: comma-separated location codes (US, GB, DE) — countries or regions, not worldwide.
The values say how large a share of each place's own searches the term takes, so a small
country can score above a large one; they are not search counts.

Input parameters:

- `category` (integer)
- `geos` (string, required)
- `keyword` (string, required)
- `points` (integer)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `keyword_overview` (~97 tokens)

The whole Google Trends page for one term in a single call: curve, direction, top places, related searches.

Use it as the first look at a keyword. It makes four requests; a part that Google refuses
is reported and the rest is still returned.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `compare_many` (~181 tokens)

Rank 6 to 25 terms on one scale — past Google Trends' limit of five per comparison.

Google rescales every comparison to its own maximum, so two separate five-term charts
cannot be read against each other. This tool runs the terms in groups that all contain one
shared *anchor* term and uses it to bring every group onto a single scale.

anchor: the shared term. Blank = chosen automatically (a mid-sized term among the first five,
which keeps both large and small terms measurable).
Returns each term's average, peak and latest value, where the largest average is 100.
Costs two requests per group of four terms.

Input parameters:

- `anchor` (string)
- `category` (integer)
- `geo` (string)
- `keywords` (string, required)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `seasonality` (~176 tokens)

The yearly rhythm of a term: which months it peaks and dips, how reliably, and when to publish for it.

Uses five years of data by default ("all" goes back to 2004). Growth or decline is removed
first, so a rising term is not mistaken for a seasonal one. Returns a month-by-month index
(100 = an average month), the peak and trough, how consistent the pattern is from year to
year, year averages, the months ahead on the current rhythm, and a publishing date.

lead_weeks: how long before demand starts to climb the content should be live.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `lead_weeks` (integer)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `trend_momentum` (~140 tokens)

Is each term growing, fading, flat or exploding — with the numbers behind the verdict.

Each term (up to 8) is measured on its own scale, so a small term's shape is not flattened
by a large one. Per term: year-over-year change of the last quarter, last quarter against
the quarter before, the long-run slope, where it stands against its own peak, and a label:
breakout, rising, stable, declining or new.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keywords` (string, required)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `find_spikes` (~139 tokens)

The moments a term suddenly jumped: when each spike started, when it peaked, how long it lasted and how big it was.

A spike is a run of points at least `threshold` times the term's usual level around that
date (its median over the surrounding year). Use it to date events, launches, outages and
news cycles, or to tell a one-off burst from real growth.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keyword` (string, required)
- `limit` (integer)
- `property` (string)
- `threshold` (number)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `share_of_search` (~149 tokens)

Share of search: your brand's portion of all searches for you and up to 4 competitors, and how it is moving.

Share of search tracks market share closely in many categories and moves before it, which
makes it a cheap leading indicator. Returns each brand's share over the whole range, at
its start and at its end (first and last fifth of the range), and the change in points.
Use topic ids (find_topic) when a brand name has other meanings.

Input parameters:

- `brand` (string, required)
- `category` (integer)
- `competitors` (string, required)
- `geo` (string)
- `property` (string)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `content_calendar` (~119 tokens)

A publishing calendar from seasonality: for up to 8 topics, when each peaks and the date its content must be live.

Each term's five-year rhythm is measured; the result is sorted by what needs publishing
soonest. Terms without a yearly pattern are listed as evergreen.
lead_weeks: how long before demand starts to climb the content should be published.

Input parameters:

- `category` (integer)
- `geo` (string)
- `keywords` (string, required)
- `lead_weeks` (integer)
- `property` (string)

Output parameters:

- `result` (string)

### `daily_history` (~174 tokens)

Day-by-day interest over a long range — Google Trends itself only gives daily data for up to ~9 months.

The range is fetched as overlapping 8-month windows and the windows are joined on one
0-100 scale using the days they share. Up to about 4 years (8 windows, two requests each).
Also returns the weekday pattern: which days of the week the term is searched most.

start, end: YYYY-MM-DD; end defaults to today.
points: rows to return (the daily series is averaged down to this many); the summary is always given.

Input parameters:

- `category` (integer)
- `end` (string)
- `geo` (string)
- `keyword` (string, required)
- `points` (integer)
- `property` (string)
- `start` (string, required)

Output parameters:

- `result` (string)

### `keyword_ideas` (~137 tokens)

Keyword ideas from what people actually search next: rising and top related queries for up to 5 seed terms, merged.

The same query coming from several seeds is listed once; each idea shows which seeds it came from —
an idea related to several seeds sits at the centre of the subject. Rising ideas are sorted
breakouts first: these are the searches that did not exist a period ago.
Costs two paced requests per seed.

Input parameters:

- `category` (integer)
- `geo` (string)
- `limit` (integer)
- `property` (string)
- `seeds` (string, required)
- `timeframe` (string)

Output parameters:

- `result` (string)

### `snapshot_trending` (~169 tokens)

Save the current Trending Now list to the local history, so it can still be searched after Google drops it.

Google shows a trend for about a week; after that there is no way to ask what was trending.
Each call stores every trend for the given countries (a trend seen again is updated, not
duplicated). Run it on a schedule — `gtrends-mcp-full snapshot US,GB` from cron does the
same — and use trending_history to query the result.

geos: comma-separated country or region codes (up to 12); blank = the default location, else US.
hours: look-back window to save, 1-191. 24 is right for a daily schedule.

Input parameters:

- `geos` (string)
- `hours` (integer)

Output parameters:

- `result` (string)

### `trending_history` (~136 tokens)

Search the saved Trending Now history: when something trended, how big it got and how long it lasted.

Works on what snapshot_trending has stored — no network. With no filter it lists the
biggest saved trends of the period.

contains: text the trend's title or queries must contain, as whole words.
geo: one location code; blank = every saved location.
days: how far back to look, counted from the trend's start.

Input parameters:

- `contains` (string)
- `days` (integer)
- `geo` (string)
- `limit` (integer)
- `min_volume` (integer)

Output parameters:

- `result` (string)

### `watchlist_add` (~85 tokens)

Put terms on the watchlist so watchlist_report tracks their direction over time.

keywords: comma-separated terms or topic ids. geo: the location to track them in (blank = default).
note: an optional label, e.g. the client or campaign they belong to.

Input parameters:

- `geo` (string)
- `keywords` (string, required)
- `note` (string)

Output parameters:

- `result` (string)

### `watchlist_remove` (~44 tokens)

Take terms off the watchlist. Blank geo removes them from every location; their past readings are kept.

Input parameters:

- `geo` (string)
- `keywords` (string, required)

Output parameters:

- `result` (string)

### `watchlist_report` (~116 tokens)

The watchlist measured now: each term's direction, what changed since the last report, and whether it is trending today.

Every run stores a reading per term, so the next report can say "was stable, now rising".
Terms are measured over five years, one at a time (two requests each): `limit` terms per
call, `offset` to continue. Also checks today's Trending Now list for each term.

Input parameters:

- `geo` (string)
- `limit` (integer)
- `offset` (integer)

Output parameters:

- `result` (string)

### `history_sql` (~183 tokens)

Run a read-only SQL SELECT on the local data file, for questions the other history tools do not cover.

Tables:
trending(geo, title, qkey, started, ended, volume, growth, categories, breakdown, first_seen, last_seen)
  — one row per saved trend; times are unix seconds UTC; categories and breakdown are JSON lists.
snapshots(id, taken_at, geo, hours, trends) — one row per snapshot_trending run.
watchlist(keyword, geo, note, added_at)
readings(keyword, geo, taken_at, latest, average, yoy, label) — one row per watchlist_report measurement.
Example: SELECT title, volume, datetime(started,'unixepoch') FROM trending WHERE geo='US' ORDER BY volume DESC LIMIT 20

Input parameters:

- `limit` (integer)
- `query` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full#diagnostics

## Score history

- 2026-10-18: 62
- 2026-10-17: 62
- 2026-10-16: 62
- 2026-10-15: 61
- 2026-10-14: 61
- 2026-10-13: 60
- 2026-10-12: 55
- 2026-10-08: 65
- 2026-10-04: 70
- 2026-10-03: 70
- 2026-10-02: 55

## Common questions

### What is the Google Trends MCP server?

Google Trends is an MCP server listed in the public MCP registry as io.github.mamrrez/gtrends-mcp-full. Google Trends: Trending Now, interest over time, regions, related searches. No API key. This page covers its PyPI package (gtrends-mcp-full).

### Is the Google Trends MCP server safe to use?

Google Trends scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Google Trends MCP server expose?

Google Trends exposes 32 tools: get_capabilities, check_endpoints, find_location, find_category, find_topic, and 27 more. Their descriptions and schemas cost roughly 4,397 tokens of context every time the server is loaded.

### Is the Google Trends MCP server still maintained?

Google Trends is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Google Trends MCP server under?

Google Trends declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/gtrends-mcp-full/
- Socket report: https://socket.dev/pypi/package/gtrends-mcp-full
- Repository: https://github.com/mamrrez/gtrends-mcp-full
- Website: https://hasanpour.com/tools/google-trends-mcp/
- Changelog RSS feed: https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full.xml
- Changelog JSON feed: https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full.json
- HTML version of this page: https://verifymcp.io/servers/mamrrez-gtrends-mcp-full/gtrends-mcp-full