Conformance witness · observation, not accusation · recomputable

Tool-surface change observed — www.detextit.com

Endpoint: https://www.detextit.com/api/mcp

Version string served, unchanged across both observations: 0.3.3

Change first observed: 2026-10-01T19:40:04.136Z

Finding: CLASS_SUSPENDED

Surface expanded without a version change — clients pinned to this version approved a smaller set of tools than is now served.

What we observed

Two anonymous tools/list enumerations of the endpoint above, at different times.

The serverInfo.version string was byte-identical in both. The tool set was not.

Tools present in the later enumeration but not the earlier (1):

Why this may matter to your users

A client that pinned 0.3.3 and reviewed the tool list at

pin time is, today, being served a different list under the same version string. Gateways

and MCP hosts that cache an approved tool set per version will not re-request approval,

because from their side nothing announced a change.

Verify this yourself

This is a plain MCP handshake. No credentials, nothing of ours required:

curl -s -X POST 'https://www.detextit.com/api/mcp' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-06-18' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"check","version":"1"}}}'
# then, with the returned Mcp-Session-Id:
curl -s -X POST 'https://www.detextit.com/api/mcp' \
  -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-06-18' -H 'Mcp-Session-Id: <id>' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

Our surface hashes over the sorted tool names plus sorted input-schema property names:

observationsurface hash
earlier9e8713f7ef2418f5aa44f8dd9b83dc7119187bd37db5e1a5fc656142a336ac7c
laterdc03e2a62222f2fbe51a385fa9b4018fbcb40851560c12a6e14902ce1e5cef48

If your own enumeration disagrees with the later hash, we are wrong and we want to hear it.

What this report does NOT say

deploy produces exactly this signal, and that is the most likely explanation.

under an unchanged version string.

Absence from our view is not absence from your server.

Method

Unannounced periodic re-enumeration of a live MCP population — we ask the endpoint

directly on a schedule rather than waiting to be notified. Relevant because only

6.4% of live MCP servers have a working channel to announce a change at all

(69.1% never declare tools.listChanged; of those that do, most expose no

server-initiated stream to send it on). A change like the one above cannot reach a

notification-based monitor, which is why it is normally invisible.


*StillOS Digital Holdings — continuous conformance witness for MCP servers.*

*Report generated 2026-10-30T17:18:50.147Z from observations dated 2026-10-01T19:40:04.136Z.*

Is this your server?

If anything here is wrong — a change you did not make, a hash that does not match, a host that was reassigned to you — tell us and we will correct or remove this page. No proof required to request removal; the record is whatever we observed, and your word about your own host outranks it.

Free. Goes to a human. Or email stillmarcus24@gmail.com.