Pass source google search for a weekly Search interest series, or source news sentiment for a 0-100 tone series. Rank on type Google Trends is a different tool.
Live data as of 2026-10-17
Source google search on get_growth and get_time_series returns a weekly 0-100 Google Search interest series for one phrase. Source news sentiment returns a weekly 0-100 tone series for the same phrase, with no volume field and with series field datatype instead of source. Both pulls on October 17, 2026 used the string tesla. Google Search held 260 weekly points from 2021-10-23 through 2026-10-10 and closed 41.0 with series volume 6323299. News sentiment held 261 weekly points from 2021-10-16 through 2026-10-10 and closed 100.0. The 12M window moved in opposite directions: Google Search minus 22.64 percent from 53.0, news sentiment plus 34.77 percent from 74.2. Live boards use type Google Trends, not those source strings.
The October 17, 2026 pull is the split that still matters next month: same close Saturday, then opposite 12M signs. get_time_series for tesla on source google search returned 260 weekly points from 2021-10-23 (value 38, volume 5860619) through 2026-10-10 (value 41, volume 6323299). Peak 100 sat on 2025-03-15 at volume 15422680. The series field is source google search. Growth metadata printed total_data_points 260.
REST get_time_series for tesla on source news sentiment returned 261 weekly points from 2021-10-16 (value 74.7) through 2026-10-10 (value 100.0). Peak 100 sat on that last Saturday. No row carried a volume key. The series field is datatype news sentiment. Growth metadata printed total_data_points 261. Peak week is not shared. Search peaked in March 2025. Sentiment peaked on the close date of this pull.
Growth windows line up by preset name and split by sign. Google Search tesla 7D matched 1W: 41.0 from 45.0, minus 8.89 percent, recent_date 2026-10-10, baseline 2026-10-03. 14D: 41.0 from 51.0, minus 19.61 percent. 30D matched 1M: 41.0 from 48.0, minus 14.58 percent. 3M was minus 22.64 percent from 53.0 on 2026-07-11. 12M was minus 22.64 percent from 53.0 on 2025-10-11. YTD was minus 4.65 percent from 43.0 on 2026-01-03. News sentiment tesla 7D matched 1W: 100.0 from 51.2, plus 95.31 percent. 14D: 100.0 from 82.9, plus 20.63 percent. 30D matched 1M: 100.0 from 43.1, plus 132.02 percent. 3M was plus 33.87 percent from 74.7 on 2026-07-11. 12M was plus 34.77 percent from 74.2 on 2025-10-11. YTD was plus 46.63 percent from 68.2 on 2026-01-03.
| Window | Search close | Search growth | Sentiment close | Sentiment growth |
|---|---|---|---|---|
| 7D / 1W | 41.0 from 45.0 | -8.89% | 100.0 from 51.2 | +95.31% |
| 14D | 41.0 from 51.0 | -19.61% | 100.0 from 82.9 | +20.63% |
| 30D / 1M | 41.0 from 48.0 | -14.58% | 100.0 from 43.1 | +132.02% |
| 3M | 41.0 from 53.0 | -22.64% | 100.0 from 74.7 | +33.87% |
| 12M | 41.0 from 53.0 | -22.64% | 100.0 from 74.2 | +34.77% |
| YTD | 41.0 from 43.0 | -4.65% | 100.0 from 68.2 | +46.63% |
Search 3M and Search 12M printed the same minus 22.64 percent because both baselines sat at 53.0, one on 2026-07-11 and one on 2025-10-11. Sentiment 3M plus 33.87 percent and 12M plus 34.77 percent did not collapse that way. Read the baseline dates. A matching percent on Search is not a matching window.
Follow-up for Search history lives on the Google search data page. Tone history lives on news sentiment data. Google News search, a third weekly 0-100 series with no volume, is a separate source on Google Search vs Google News.
Google Search tesla printed estimated volume. News sentiment tesla printed none. Those are two different payloads on the same keyword. A comma-separated get_growth call is supposed to join them. On this pull it did not.
{"mode": "get_growth", "source": "google search, news sentiment", "keyword": "tesla", "percent_growth": ["7D", "30D", "12M"]}
That MCP comma call on October 17, 2026 returned sources_requested 2, sources_processed 2, sources_successful 1, and sources_failed 1. The Search row matched the dedicated 7D, 30D, and 12M prints. The news sentiment row printed status unavailable and message Source did not respond in time. trend_analysis then counted only the successful source: uptrend_ratio 0/1, uptrend_percentage 0.0, total_sources_analyzed 1. A timeout is not a downtrend vote. It is a missing vote.
volume_weighted_growth was -8.89 with has_volume_data true, sources_with_volume 1, weight_coverage 1/1 sources, and total_volume 6320000.0. The only weighted row was Google Search, at 100 percent of that volume, using Search 7D growth minus 8.89. Sentiment plus 95.31 percent never entered, because the mixer never received it. Search 12M minus 22.64 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.
Dedicated MCP get_growth and get_time_series for tesla on source news sentiment returned CloudFront HTTP 504 HTML. REST then printed. A later REST retry of tesla 12M, plus bitcoin, nvidia, openai, and nike on the same source, returned 504 again. Quote those timeouts. Do not invent a 12M sentiment row for those other names from a 504. Dedicated Search growth for those names did return: bitcoin closed 21.0, 12M minus 60.38 percent from 53.0, 260 points, no volume keys. nvidia closed 27.0, 12M minus 48.08 percent from 52.0, estimated volume 3290000.0. openai closed 10.0, 12M minus 83.33 percent from 60.0, no volume keys. nike closed 52.0, 12M minus 10.34 percent from 58.0, estimated volume 19700000.0.
get_time_series rejects the comma. Source google search, news sentiment returned HTTP 200 with envelope statusCode 400, error invalid_source, message 'google search, news sentiment' is not a valid source., and listed 16 keyword sources with no all. One source per series call. Two sources belong on get-growth.
News sentiment tesla series points had date, value, keyword, and datatype only. Growth rows had no volume_available key. Source news sentiment is a 0-100 tone index. It is not source news volume, which is a separate keyword source with an article-count field when the pipeline has it. REST get_growth for tesla on source news volume returned CloudFront HTTP 504 on this run. Mention count is not on this page.
Google Search volume is keyword-dependent. tesla printed volume_available true, volume_estimated true, recent_volume 6320000.0, and volume_growth null. The series integer on 2026-10-10 was 6323299. Baseline 7D volume printed 6940000.0 against series 6940206 on 2026-10-03. nike printed estimated volume 19700000.0 on close 52.0. nvidia printed 3290000.0 on close 27.0. bitcoin and openai 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 sentiment close 100.0. Sentiment 7D plus 95.31 percent from 51.2 is a jump off a mid-index baseline, not a doubling of Search demand. Search 7D on that keyword was minus 8.89 percent from 45.0. Quote both closes. Do not rescale one source onto the other.
REST source news_sentiment (one token, no space) returned HTTP 200 with envelope statusCode 400, error invalid_source, message "'news_sentiment' is not a valid source.", and listed 17 names including all. The space is required. Store news sentiment.
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. Tone follow-up lives on news sentiment data. Headline follow-up is type Google News Top News, not source news sentiment.
{"mode": "get_growth", "source": "google search, news sentiment", "keyword": "tesla", "percent_growth": ["30D", "12M"]}
{"mode": "get_time_series", "source": "google search", "keyword": "tesla"}
{"mode": "get_time_series", "source": "news sentiment", "keyword": "tesla"}
{"mode": "get_top_trends", "type": "Google Trends"}
The MCP equivalents are get_growth(keyword="tesla", source="google search, news sentiment", percent_growth=["30D", "12M"]), get_time_series(keyword="tesla", source="google search"), get_time_series(keyword="tesla", source="news sentiment"), and get_top_trends(type="Google Trends"). REST 1W matched 7D on tesla for both sources that returned. REST 1M matched 30D on both.
REST type google search (the keyword source string, lowercase) returned HTTP 200, echoed type Google Trends, as_of_ts 2026-10-17T06:01:33.049421+00:00, and matched rj mitte at rank 1. REST type news sentiment returned HTTP 200 with envelope statusCode 400, error invalid_request, message Unknown type 'news sentiment', plus 24 valid feed labels. llms.txt still describes feed labels as case-sensitive. The live handler accepted google search as an alias on October 17, 2026 and rejected news sentiment. Prefer the canonical Google Trends spelling in stored configs. Do not pass source news sentiment as a feed type.
get_growth with source Google Trends and keyword tesla returned HTTP 200 with envelope statusCode 400, error invalid_source, message "'google trends' is not a valid source.", plus 17 names including all. The handler lowercased the rejected type string. It did not map it to source google search. get_time_series on source Google Trends failed the same way and listed 16 names with no all.
REST omitting type is a different 400. POST https://api.trendsmcp.ai/api with mode get_top_trends and limit 1, 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. Keyword follow-up stays on source google search or source news sentiment. The live board stays on type Google Trends.
FAQ