Score a page or draft against 11,485 public taxonomy categories (Google Ads Topics, Google Merchant, IAB Content 3.1, IAB Audience 1.1, IAB Ad Product 2.0, LinkedIn Industries v2) by embedding similarity, rank it per taxonomy, and get the phrases that pull it toward a target category. Free. A topical-alignment check for content briefs and SEO/GEO audits, not a ranking predictor.
9 verified, 0 failed, 0 observed risk, 1 not checked, on 22 November 2026. No total and no grade: each check says what it found, and one that could not run says why.
Every x402 payment we hold to the address the catalogue lists for this server’s paid tools (0x88ff…a443), payments an address made to itself left out. The same address takes payment for 3 other catalogued services, so these figures are an upper bound for this server.
5 tools on the last day the list was read, fingerprint f4976132c4c7f5e300a.
Score Text
Scores text against every category in all six taxonomies (one embedding, cosine similarity) and returns the top `per` rows per taxonomy. With `taxonomy` and `category` it also returns the target's rank, score, gap to #1, and a phrase bank split into phrases the text already uses and phrases it does not. Read the rank and the gap, not the raw percent (scores compress into a 70 to 90 band). Free; read-only and safe to retry.
read-onlyadditive onlysafe to repeatclosed worldas the server describes it; we do not call tools
| Name | Type | Required | Description |
|---|---|---|---|
| text | string | yes | The page or draft text to score, as plain text or HTML (tags are stripped). 1 to 32768 characters. URLs are not fetched; send the content. |
| taxonomy | string | no | Taxonomy of the target category. |
| category | string | no | Target category id, full path, or a unique path substring within the taxonomy (use topic_scorer_find to look one up). |
| per | integer | no | Rows per taxonomy. |
| phrases | integer | no | Phrase bank size for the target category (0 skips it). |
| full | boolean | no | Score the whole text as the mean of 8,192-char chunks instead of only the first 8,192 chars. |
No agent registration names this server; we probe it on our own list.
A day counts as answered only when every timed run that day got every request answered; the hourly runs began 5 November 2026. Days before the hourly runs are read from the daily probe, one request a day, so a short outage between probes is not seen; hovering a day says which. Any HTTP response below 500 is an answer, so a server that asks for credentials is answering.
| Day | State | Timed runs | From |
|---|---|---|---|
| 2026-11-22 | Answered | 14 | hourly runs |
| 2026-11-21 | Some runs failed | 23 | hourly runs |
| 2026-11-20 | Some runs failed | 24 | hourly runs |
| 2026-11-19 | Answered | 23 | hourly runs |
| 2026-11-18 | Some runs failed | 24 | hourly runs |
| 2026-11-17 | Answered | 23 | hourly runs |
| 2026-11-16 | Answered | 24 | hourly runs |
| 2026-11-15 | Answered | 23 | hourly runs |
| 2026-11-14 | Some runs failed | 24 | hourly runs |
| 2026-11-13 | Answered | 23 | hourly runs |
| 2026-11-12 | Answered | 23 | hourly runs |
| 2026-11-11 | Answered | 23 | hourly runs |
| 2026-11-10 | Answered | 24 | hourly runs |
| 2026-11-09 | Some runs failed | 23 | hourly runs |
| 2026-11-08 | Answered | 24 | hourly runs |
| 2026-11-07 | Answered | 18 | hourly runs |
| 2026-11-06 | Answered | 23 | hourly runs |
| 2026-11-05 | Answered | 4 | hourly runs |
Each day: the median of that day’s runs’ p50 (the line) and of their p95 (the top of the band), in milliseconds, from our server in Europe to the response headers of an MCP initialize request. An observation, not a threshold.
| Day | p50 ms | p95 ms | Runs |
|---|---|---|---|
| 2026-11-22 | 158 | 258 | 14 |
| 2026-11-21 | 168 | 274 | 22 |
| 2026-11-20 | 161 | 266 | 23 |
| 2026-11-19 | 167 | 264 | 23 |
| 2026-11-18 | 161 | 276 | 23 |
| 2026-11-17 | 156 | 272 | 23 |
| 2026-11-16 | 158 | 257 | 24 |
| 2026-11-15 | 156 | 239 | 23 |
| 2026-11-14 | 157 | 273 | 23 |
| 2026-11-13 | 154 | 262 | 23 |
| 2026-11-12 | 166 | 271 | 23 |
| 2026-11-11 | 150 | 266 | 23 |
| 2026-11-10 | 158 | 270 | 24 |
| 2026-11-09 | 163 | 282 | 22 |
| 2026-11-08 | 151 | 273 | 24 |
| 2026-11-07 | 155 | 243 | 18 |
| 2026-11-06 | 158 | 272 | 23 |
| 2026-11-05 | 150 | 244 | 4 |
Each hour: the median p50 of that hour’s runs, times in UTC; the shaded last hour is not complete. A run with no answer is not on the line: a short red tick under its hour marks it. Latest run 22 November 2026, 13:38 UTC: 5 of 5 requests answered, p50 142 ms, p95 281 ms.
| Hour (UTC) | p50 ms | Runs | With no answer |
|---|---|---|---|
| 2026-11-22 14:00 (now) | — | 0 | 0 |
| 2026-11-22 13:00 | 142 | 1 | 0 |
| 2026-11-22 12:00 | 168 | 1 | 0 |
| 2026-11-22 11:00 | 152 | 1 | 0 |
| 2026-11-22 10:00 | 159 | 1 | 0 |
| 2026-11-22 09:00 | 184 | 1 | 0 |
| 2026-11-22 08:00 | 197 | 1 | 0 |
| 2026-11-22 07:00 | 158 | 1 | 0 |
| 2026-11-22 06:00 | 145 | 1 | 0 |
| 2026-11-22 05:00 | 215 | 1 | 0 |
| 2026-11-22 04:00 | 166 | 1 | 0 |
| 2026-11-22 03:00 | 187 | 1 | 0 |
| 2026-11-22 02:00 | 154 | 1 | 0 |
| 2026-11-22 01:00 | 144 | 1 | 0 |
| 2026-11-22 00:00 | 149 | 1 | 0 |
| 2026-11-21 23:00 | 190 | 1 | 0 |
| 2026-11-21 22:00 | 145 | 1 | 0 |
| 2026-11-21 21:00 | 178 | 1 | 0 |
| 2026-11-21 20:00 | 168 | 1 | 0 |
| 2026-11-21 19:00 | 169 | 1 | 0 |
| 2026-11-21 18:00 | 178 | 1 | 0 |
| 2026-11-21 17:00 | 158 | 1 | 0 |
| 2026-11-21 16:00 | 148 | 1 | 0 |
| 2026-11-21 15:00 | — | 1 | 1 |