google-trends-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | Yes | Your Apify API token, copied from Settings > API & Integrations in the Apify console. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_interest_over_timeA | Get Google Trends search interest (0-100) over time for one keyword, optionally with interest by region (US states, regions of a country, or countries when worldwide). Use it to see if a topic is rising, find its peak, or compare seasons. Call once per keyword: each series is scaled 0-100 on its own peak. |
| get_trending_searchesA | Get what people are searching for right now on Google in a country: the trending searches of the last 4, 24, 48 or 168 hours, with search volume and related queries. Use it for news, content ideas or market monitoring. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools target clearly different things: current trending searches in a country versus historical interest for a specific keyword. An agent can pick correctly from the names and descriptions alone, with no overlap in shape of output.
Both tools follow the same predictable get_<resource> pattern (get_trending_searches, get_interest_over_time), using snake_case throughout. No mixed conventions.
Two tools is thin for a Google Trends server, which naturally exposes several distinct query modes. It's a defensible minimal surface, but it sits at the borderline of feeling under-scoped.
Core read paths are covered (trending now, interest over time with optional regional breakdown), but there is no multi-keyword comparison, no dedicated related-queries/related-topics tool, and no trending-topics variant. The description explicitly says to call once per keyword, confirming comparison is a gap agents must work around.