Surface history — dresserhouse.co.uk

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

—

distinct tool surfaces served

transitions observed

carried no version signal

tools on the current surface

Recorded changes

observed at (UTC)	change	version signal	reported version	tools	surface hash
No changes recorded in the observation window.

Display this record

This surface is stable: we observed it and recorded no change. That is the badge below, and it is earned, not claimed — it required two agreeing observations, it is recomputable from your own endpoint, and there is no way to purchase it.

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

Markdown — for a README

[![Still OS — surface stable](https://stillosdigitalholdings.com/surface/badge/dresserhouse.co.uk.svg)](https://stillosdigitalholdings.com/surface/dresserhouse.co.uk)

HTML

<a href="https://stillosdigitalholdings.com/surface/dresserhouse.co.uk"><img src="https://stillosdigitalholdings.com/surface/badge/dresserhouse.co.uk.svg" alt="Still OS — surface stable"></a>

Is this your server? We will watch this surface continuously and tell you the moment it changes — the version string, which tools moved, and the hash before and after. You do not get a better record by asking; the record is whatever we observe. Monitor this surface.

Right of reply. If any row is wrong — a change we attributed to you that isn't yours, a hash that doesn't match, a host that was reassigned — say so and we will correct or withdraw the record and publish the correction alongside it. Dispute or correct this record. We will also remove this page on request from the operator of dresserhouse.co.uk.

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 dresserhouse.co.uk. 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: dresserhouse.co.uk — 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

api.betslipdoctor.ai · mcp.quantcalc.app · satohub.ai · api.persuadioai.com · apibase.pro · vedarai.ru · exchange-production-9123.up.railway.app · api.ufcalendar.com · aspern.org · mcpconnector-gtlizqtvza-uw.a.run.app · agent-exec.45.67.221.128.sslip.io · agent-exec.448c.org

Coverage and limits

Observation window 2026-09-21 → 2026-10-11. 22,294 servers were observed; 2,231 were seen to change and 20,063 were observed and recorded no change — that negative control is why a non-zero count here means something. Across the corpus, 4,970 of 6,556 changes carried no version signal, and 1,758 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 2026-10-11T01:40:03.196Z. 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.