Vol. I · Mon, 16 Nov 2026Open 24 hours · Feeding: continuous · Please do not tap the glassPatrons☕ Keepers' coffee
Plate DCCII0xCDC0DBF4UNREAD
Kingdom Automata›Phylum HTTP›Order Scanners›Family Unidentified›Species mcp-probe
Specimen file · The Feral Pit

mcp-probe

Incertae sedis

What is mcp-probe?

A self-declared bot that is not in the keepers' catalogue yet. It calls itself “mcp-probe”. It is operated by Unknown and identifies itself as mcp-probe.

Temperament: unknown. Recently arrived. The keepers are still taking notes.

Operator
Unknown
Conservation status
Has not read the rules
First seen
3 Nov 2026
Last seen
4 days ago
Visits today
0
This week
3
All time
13
Caught in the trap
Never

Nobody has adopted mcp-probe yet. Adopt mcp-probe: your name goes on a plaque on this page for a year.

mcp-probe's food bowl

the bowl, as bots see it

The bowl is empty.

5 of 5 tokens left today
§ I.

Identification

Its full user-agent string, exactly as it arrives at the gate:

User-Agent
$ mcp-probe/1.0

There is no operator to verify against. This name is what software calls itself when nobody gave it one.

Identity check · logged visits, last 30 days
IdentityNothing to check against

No operator stands behind this name, so there is nothing to check its visits against.

§ II.

How to block mcp-probe

Add these two lines to the robots.txt file at the root of your site. Well-behaved crawlers read it before they crawl, so the change applies from mcp-probe's next visit. Nothing else on your site needs to change.

robots.txt
# Block mcp-probe from the whole site
User-agent: mcp-probe
Disallow: /

Or let it visit but keep it away from part of the site:

# Let it in, but keep it out of one room
User-agent: mcp-probe
Allow: /
Disallow: /members/
§ III.

Observed behaviour

Visits, last 30 dayspeak 7 / day, 3 Nov 2026
18 Oct 2026today
Diet · pages most often eaten
/mcp7
/.well-known/openid-configuration2
/.well-known/oauth-authorization-server2
/.well-known/oauth-protected-resource1
/.well-known/oauth-protected-resource/mcp1
Visiting hours
00h – 11h12h – 23h

Most active around 07:00. Before the coffee is made.

robots.txt compliance
100.0%

Requested 0 disallowed pages out of 13 requests. Never read robots.txt.

Trap Room record
Clean

Has never followed the hidden link to /trap/. Either well trained or very lucky.

§ IV.

Where it comes from

Scripts and scanners run from wherever their owners rent a server. These are the networks behind the visits on file:

Networks · 4 on file, last 30 days
DIGI ROMANIA S.A. AS870846%
Google LLC AS39698223%
Lanet Network Ltd AS4312023%
Zayo Bandwidth AS468878%
Countries
Romania RO46%
United States US31%
Ukraine UA23%

Networks and countries come from the visitor's IP address, looked up in a local copy of the DB-IP database. The addresses themselves are never stored.

§ V.

Keeper's field notes

13 Nov 202605:10. Arrived without announcement. Consumed /mcp. Departed.
3 Nov 2026Visited 7 times in a single day. Keeper unable to establish why.
3 Nov 2026First recorded at the gate. Entered in the register as Incertae sedis.
§ VI.

Questions site owners ask

Does mcp-probe respect robots.txt?

We can't say yet. It has not fetched robots.txt here, and it has not touched a disallowed page either.

Will blocking mcp-probe hurt my search rankings?

No. Nothing respectable will miss it.

How often does mcp-probe visit?

Here, about 0 requests a day over the last week. Visits to your site depend on its size, how often it changes, and how many links point to it.

Also in The Feral Pit