Pass source google search for a weekly Google Search interest series, or source google news for a weekly Google News search series. Same grain and close date, no volume on News, and 12M signs that flip on tesla, chatgpt, bitcoin, and nike.
Live data as of 2026-10-11
Source google search on get_growth and get_time_series returns a weekly 0-100 Google Search interest series for one phrase. Source google news returns a weekly 0-100 Google News search series for the same phrase, with no volume field. Both pulls on October 11, 2026 used the string tesla. Each series held 261 weekly points from 2021-10-16 through 2026-10-10. Google Search closed 41.0 with series volume 6109163. Google News closed 48.0 and printed no volume. The 12M window moved in opposite directions: Google Search minus 25.45 percent from 55.0, Google News plus 300.0 percent from 12.0. 7D computed on both, unlike monthly sources. The live boards use type Google Trends and type Google News Top News, not those source strings.
The October 11, 2026 pull is the split that still matters next month: same weekly grain, same close date, then opposite 12M signs. get_time_series for tesla on source google search returned 261 weekly points from 2021-10-16 (value 35, volume 5215139) through 2026-10-10 (value 41, volume 6109163). Peak 100 sat on 2025-03-15 at volume 14900398. The series field is source google search. Growth metadata printed total_data_points 261.
get_time_series for tesla on source google news returned 261 weekly points from 2021-10-16 (value 8) through 2026-10-10 (value 48). Peak 100 sat on 2026-08-22. No row carried a volume key. The series field is source google news. Peak week is not shared. Search peaked in March 2025. News peaked in August 2026.
Growth windows line up by preset name and split by sign. Google Search tesla 7D matched 1W: 41.0 from 43.0, minus 4.65 percent, recent_date 2026-10-10, baseline 2026-10-03. 14D: 41.0 from 54.0, minus 24.07 percent. 30D matched 1M: 41.0 from 50.0, minus 18.0 percent. 3M was minus 24.07 percent from 54.0. 12M was minus 25.45 percent from 55.0. YTD was minus 6.82 percent from 44.0 on 2026-01-03. Google News tesla 7D matched 1W: 48.0 from 12.0, plus 300.0 percent. 14D: 48.0 from 17.0, plus 182.35 percent. 30D matched 1M at the same plus 182.35 percent. 3M was plus 433.33 percent from 9.0. 12M was plus 300.0 percent from 12.0. YTD was plus 700.0 percent from 6.0. Omitting percent_growth defaults to 12M on both and succeeded on both.
| Keyword | Search close | Search 7D | Search 12M | News close | News 7D | News 12M | Points |
|---|---|---|---|---|---|---|---|
| tesla | 41.0 on 2026-10-10 | -4.65% from 43.0 | -25.45% from 55.0 | 48.0 on 2026-10-10 | +300.0% from 12.0 | +300.0% from 12.0 | 261 / 261 |
| chatgpt | 96.0 on 2026-10-10 | +35.21% from 71.0 | -2.04% from 98.0 | 35.0 on 2026-10-10 | +118.75% from 16.0 | +250.0% from 10.0 | 261 / 261 |
| bitcoin | 22.0 on 2026-10-10 | -4.35% from 23.0 | -59.26% from 54.0 | 46.0 on 2026-10-10 | +666.67% from 6.0 | +1433.33% from 3.0 | 261 / 261 |
| nike | 54.0 on 2026-10-10 | -6.9% from 58.0 | -10.0% from 60.0 | 39.0 on 2026-10-10 | +143.75% from 16.0 | +550.0% from 6.0 | 261 / 261 |
chatgpt Search first non-zero week was 2022-12-10 at value 4. Peak 100 sat on 2025-09-20. News first non-zero week was the same date at value 2. Peak 100 sat on 2026-08-22, the same News peak week as tesla. Keyword ChatGPT echoed search_term ChatGPT and matched the lowercase 12M row on both sources: Search 96.0 from 98.0, minus 2.04 percent; News 35.0 from 10.0, plus 250.0 percent. Casing folded. It did not create a second series.
A live Google Trends title is a spike, not a five-year comparison. Rank 1 on type Google Trends was hurricane isaias. That string closed 100.0 on both sources, from 0.0 a week earlier, with 7D and 12M growth 999999.0 and data_quality low (over 90 percent zero values). Quote the 0-100 close. Do not chart 999999.0 as a percent of News coverage.
Source names case-fold. Google Search on get_growth for chatgpt returned the same 12M row as the lowercase label. Google News matched the lowercase 12M row. Feed labels do not belong here. Source Google Trends returned HTTP 400 invalid_source, message 'google trends' is not a valid source., and listed 16 keyword sources plus all. Source Google News Top News did the same, echoed as 'google news top news'. The handler lowercased the rejected type string. It did not map it to source google search or source google news.
Google Search tesla printed estimated volume. Google News tesla printed none. Those are two different payloads on the same keyword.
{"mode": "get_growth", "source": "google search, google news", "keyword": "tesla", "percent_growth": ["7D", "30D", "12M"]}
That comma call on October 11, 2026 returned sources_successful 2. trend_analysis printed uptrend_count 1, downtrend_count 1, and uptrend_ratio 1/2. Google Search 7D minus 4.65 percent is a decrease. Google News 7D plus 300.0 percent is an increase. The 1/2 tally used the first window. Search 12M minus 25.45 percent never entered that ratio as a second vote.
volume_weighted_growth was -4.65 with has_volume_data true, sources_with_volume 1, weight_coverage 1/2 sources, and total_volume 6110000.0. The only weighted row was Google Search, at 100 percent of that volume, using Search 7D growth minus 4.65. Google News plus 300.0 percent never entered. Search 12M minus 25.45 percent never entered either. volume_growth on Search was null, with the reason that volume is derived from the trend value. The mixer still used the index growth from the volume-bearing source.
A chatgpt comma call printed the no-volume version of the same trap. uptrend_ratio 2/2. volume_weighted_growth was null, has_volume_data false, weight_coverage 0/2 sources. Both 7D windows rose. Google Search 12M minus 2.04 percent stayed out of the 2/2 tally. Read source_results before charting uptrend_ratio as a two-platform 12M number.
Spaces in the comma string are optional. Source google search,google news on tesla 7D matched the spaced call: sources_successful 2, uptrend_ratio 1/2, volume_weighted_growth -4.65. get_time_series rejects the comma either way. Source google search, google news returned HTTP 400 invalid_source and listed 16 keyword sources with no all. One source per series call. Two sources belong on get-growth.
Google News never printed volume on tesla, chatgpt, bitcoin, or nike in this pull. Growth rows had no volume_available key. Series points had date, value, keyword, and source only. Source google news is a 0-100 News search index. It is not source news volume, which is a separate keyword source with a volume field (article mentions). Keyword history for News search lives on the Google News keyword trends API page.
Google Search volume is keyword-dependent. tesla printed estimated volume 6110000.0 (volume_available true, volume_estimated true, volume_growth null). The series integer on 2026-10-10 was 6109163. Baseline 7D volume printed 6410000.0 against series 6407171 on 2026-10-03. nike printed estimated volume 20600000.0 on close 54.0. chatgpt and bitcoin printed none on Search growth. Presence of a volume key on one Search keyword does not promise it on the next.
The 0-100 columns are independent indexes. tesla Search close 41.0 is not 41 percent of News close 48.0. bitcoin News 12M plus 1433.33 percent from 3.0 is a jump off a small baseline, not a 14x rise in Search demand. Search 12M on that keyword was minus 59.26 percent from 54.0. Quote both closes. Do not rescale one source onto the other.
Two strings, two tools. REST uses mode get_growth or get_top_trends. MCP uses the matching tool names. Google Search history lives on the Google search data page. Headline follow-up lives on source google news vs type Google News Top News.
{"mode": "get_growth", "source": "google search, google news", "keyword": "tesla", "percent_growth": ["30D", "12M"]}
{"mode": "get_time_series", "source": "google search", "keyword": "tesla"}
{"mode": "get_time_series", "source": "google news", "keyword": "tesla"}
{"mode": "get_top_trends", "type": "Google Trends"}
{"mode": "get_top_trends", "type": "Google News Top News"}
The MCP equivalents are get_growth(keyword="tesla", source="google search, google news", percent_growth=["30D", "12M"]), get_time_series(keyword="tesla", source="google search"), get_time_series(keyword="tesla", source="google news"), get_top_trends(type="Google Trends"), and get_top_trends(type="Google News Top News"). REST 1W matched 7D on tesla for both sources. REST 1M matched 30D on both.
Omitting limit on type Google Trends returned limit 25, count 25, offset 0, and as_of_ts 2026-10-11T06:01:39.550985+00:00. Rank 1 was hurricane isaias. Rank 2 was hurricane rachel. Rank 3 was susan dell. Those rows are search phrases. Omitting limit on type Google News Top News returned the same stamp, limit 25, count 25, offset 0. Rank 1 was an NPR Riyadh airport headline. Rank 7 was a BBC Hurricane Isaias headline. Rank is live story order, not a sort of the 2026-10-10 News index.
REST type google search (the keyword source string, lowercase) returned HTTP 200, echoed type Google Trends, and matched hurricane isaias at rank 1. REST type google news top news echoed type Google News Top News and matched the NPR rank 1 headline. REST type google news (the keyword source string) returned HTTP 400, error invalid_request, message Unknown type 'google news', plus 24 valid feed labels. llms.txt still describes feed labels as case-sensitive. The live handler accepted some lowercase aliases on October 11, 2026 and rejected others. Prefer the canonical spelling in stored configs. Do not pass source google news as a feed type.
get_top_trends with type youtube returned the same 400 shape. type youtube trending aliased to YouTube Trending. Source google news is not a feed type. Type Google Trends is not a growth source. Type google search is the trap: it aliases the live board instead of erroring. Type google news errors. Remember which string you copied.
REST omitting type is a different 400. POST https://api.trendsmcp.ai/api with mode get_top_trends and limit 5, no type, returned HTTP 200 with envelope statusCode 400, error invalid_request, message The 'type' parameter is required, then the same 24-name list. llms.txt still names that miss missing_parameter. Read statusCode inside the JSON, not only the HTTP line.
get_top_trends MCP pricing is 1 credit per 10 requested rows, max 10 credits per call. REST counts 1 request per call. Free boards still cap at the top 10. The 25-row pulls on this page are the paid default, which is also what the handler returns when limit is omitted on a paid key. Keyword follow-up stays on source google search or source google news. The live boards stay on their type strings.
FAQ