Surface history — apibase.pro

An observation record, not an assessment. Every row below is a change we recorded directly, with the content hash before and after. https://apibase.pro/mcp

53 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.

Recorded changes

Display this record

The badge reflects what we observed, including when that is unflattering. We offer it either way on purpose — a mark you can only display when it flatters you is an advertisement, and nobody can rely on an advertisement.

Free, no account, no attribution fee. The image updates itself as the record changes.

Markdown — for a README

[![Still OS surface record](https://stillosdigitalholdings.com/surface/badge/apibase.pro.svg)](https://stillosdigitalholdings.com/surface/apibase.pro)

HTML

<a href="https://stillosdigitalholdings.com/surface/apibase.pro"><img src="https://stillosdigitalholdings.com/surface/badge/apibase.pro.svg" alt="Still OS surface record"></a>

Ecosystem context — not specific to this server

This section is identical for ~92% of publishers and is published as shared context, not as a finding about apibase.pro. 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.

Elsewhere in this record set

We publish a separate trust and dependency assessment for this same host: apibase.pro — operator dossier. That one grades the published artifact; this one records what the endpoint actually served.

Index of everything covered: all observed hosts · machine-readable: changes feed (JSON), Atom, sitemap.

Other hosts observed around the same time

codex-reset.com · programmes.net · api.iteon.pl · loadbay.xyz · mcp.ainumbers.co · mcp.quantcalc.app · vedarai.ru · mailcheer.com · qianyuan.ltd · mcp.aiapplyd.com · api.babyblueviper.com · remnant.dedale-bi.com

Coverage and limits

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.