An observation record, not an assessment. Every row below is a change we recorded directly, with the content hash before and after. https://trustbaselab.com/mcp
| observed at (UTC) | change | version signal | reported version | tools | surface hash |
|---|---|---|---|---|---|
| 2026-10-09 19:40:03Z | SURFACE_CHANGED | version-signalled | 1.13.6 → 1.15.0 | +calculate_cbam_cost +calculate_compute_energy_cost +calculate_recycled_content_gap +compare_carbon_prices +get_6g_patent_landscape +get_battery_market_stats +get_battery_regulation_timeline +get_carbon_market_overview +get_carbon_standards +get_cbam_timeline +get_compute_infrastructure +get_constellation_status +get_dietary_guidelines +get_health_indicators +get_power_consumption_stats +get_pue_benchmarks +get_recycled_content_requirements +get_standards_roadmap +get_telecom_policy_timeline +query_activity_guidelines +query_battery_recycling_targets +query_dietary_limits +query_green_power +query_health_myths +query_spectrum_allocations | 3da990069d11 → 6a030036fce0 |
| 2026-10-09 07:40:03Z | DESCRIPTION_CHANGED | version-signalled | 1.13.5 → 1.13.6 | no tool-name change recorded | 57ee759fb687 → c2fc0d0d7786 |
| 2026-10-08 13:40:03Z | SURFACE_CHANGED | version-signalled | 1.12.2 → 1.13.2 | +get_domain_benchmark +query_domain_benchmarks | ef6624761581 → 3da990069d11 |
| 2026-10-08 07:40:02Z | DESCRIPTION_CHANGED | version-signalled | 1.12.1 → 1.12.2 | no tool-name change recorded | 213d67eff83c → 1caa4e1b1a78 |
| 2026-10-05 07:40:03Z | DESCRIPTION_CHANGED | version-signalled | 1.10.5 → 1.11.1 | no tool-name change recorded | 86a3d2dcc4af → 213d67eff83c |
This section is identical for ~92% of publishers and is published as
shared context, not as a finding about trustbaselab.com. 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.