google-trends
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRENDS_GEO | No | Default country when a tool call omits geo. | US |
| TRENDS_CACHE_TTL_MS | No | How long fetched data is reused (5 minutes). | 300000 |
| TRENDS_FETCH_TIMEOUT_MS | No | Per-request timeout. | 15000 |
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
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| trending_nowA | Fetch the latest trending Google searches for a country, with approximate search volume and a related headline for each. Use this for 'what is trending right now' questions. |
| interest_over_timeA | Compare search interest for 1-5 keywords over a time range (0-100 relative scale, like the Google Trends chart). Use this to see whether something is rising or falling in popularity. |
| related_queriesA | Get the top and rising related search queries for a keyword. 'Breakout' means the query grew by more than 5000%. |
| add_trends_to_questionA | Fetch the latest Google Trends data (trending searches, plus interest-over-time and related queries for any keywords given) and return the user's question with that data attached. Call this before answering any question that depends on what people are currently searching for, and then answer the enriched question. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask_with_trends | Fetches the latest Google Trends data and sends your question to the model with that data attached. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The three core tools (trending_now, interest_over_time, related_queries) target clearly distinct Google Trends views. However, add_trends_to_question is a composite that re-fetches trending searches plus interest-over-time and related queries, so an agent faces a real choice between the granular tools and the wrapper, and the instruction to call it 'before answering any question that depends on current searches' actively overlaps with the other three.
All names use snake_case, which is consistent, but the structural convention is mixed: trending_now and interest_over_time are adverb/noun phrases, related_queries is adjective+noun, and add_trends_to_question is a verb_noun_to_noun pattern. The result is readable but not a predictable verb_noun scheme.
Four tools is a tight, well-scoped surface for a Google Trends server, and each of the three core tools maps to a real Trends capability. The only waste is the composite add_trends_to_question, which largely duplicates the others rather than adding a new operation.
The surface covers the three most common Trends workflows (current trending, time-series interest, related queries), but notable gaps remain: no interest-by-region/subregion breakdown, no keyword suggestion or category filters, and no way to get trending by category. Agents needing geographic comparison will hit a dead end.