An observation record, not an assessment. Every row below is a change we recorded directly, with the content hash before and after. https://clink-lithium-vault.fly.dev/mcp
6 of these transitions happened while the reported version string stayed the same. A consumer pinning that version would have received a different tool surface with nothing in the version to indicate it. That is a compatibility and review fact, not a security finding and not an allegation of wrongdoing — unversioned iteration is normal practice and is frequently deliberate.
| observed at (UTC) | change | version signal | reported version | tools | surface hash |
|---|---|---|---|---|---|
| 2026-10-07 07:40:03Z | DESCRIPTION_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | no tool-name change recorded | e4e86a4b85c3 → a5aae10edca1 |
| 2026-10-06 07:40:03Z | DESCRIPTION_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | no tool-name change recorded | 76b67c50883a → e4e86a4b85c3 |
| 2026-10-06 07:40:03Z | PARAMS_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | no tool-name change recorded | bc40a445e425 → 5f92fcba3b5f |
| 2026-10-06 07:40:03Z | SURFACE_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | +x_leads_deep | 3aec67404f68 → 97d652a2ea56 |
| 2026-09-28 07:40:03Z | SURFACE_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | +pm_closing +pm_gaps +pm_resolved +pm_sentiment +pm_watch +send_feedback | 3d1eaac7d263 → 3aec67404f68 |
| 2026-09-25 19:40:04Z | SURFACE_CHANGED | SILENT — version string did not move | 0.2.0 (unchanged) | +web_answer +x_list | 08c0d7d68d00 → 3d1eaac7d263 |
This section is identical for ~92% of publishers and is published as
shared context, not as a finding about clink-lithium-vault.fly.dev. 90 dependency
packages sit beneath the measured MCP population; 41 have a
single maintainer and 31 have not published in over two years.
The widest is zod at
80.46% of npm-backed servers (8529 servers,
1 maintainer, last publish 2026-09-13).
These are properties of the shared SDK dependency closure. Any page claiming this set as
one operator's personal exposure is misreading a universal fact as a private one.
Source: state/mcp-census/chokepoint-maintainers.json, as_of 2026-10-07.
Observation window 2026-09-21 → 2026-10-10.
22,294 servers were observed; 2,214
were seen to change and 20,080 were observed and
recorded no change — that negative control is why a non-zero count here means something.
Across the corpus, 4,781 of
6,334 changes carried no version signal, and
1,690 of those added or removed tools.
What this does NOT cover: servers outside the observed set; changes that
occurred before 2026-09-21; changes that began and reverted between two observations;
and any server reachable only with credentials we do not hold. A server's absence from this
record is not evidence it did not change — only that we did not observe it.
Universe captured 2026-10-10T19:40:03.823Z. Produced by core/surface_history_page.cjs (reads core/surface_clock producers).
Hashes are of the served tool surface and are recomputable from the server's own response.