Atlas entry

`blckalpaca.at`

20 capabilities over ARD, MCP and OpenAPI. The inventory is incomplete. First atlas observation.

Observed 10 Nov 2026, 12:50 UTC · passive: no tools called, no credentials sent · sha256:df6e3d…574a

20 capabilities. 4 only read. 2 change records, and 1 of those deletes or cancels. 2 send messages. 11 have no reading.

AI reading, beta. side-effects v1 on jev-1.14.0 and claude-haiku-5.5, calibrated on OpenAPI and MCP (golden-1 and golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.

AI readings summary · beta

The service lists 20 capabilities, and 9 have AI readings.

unsubscribeNewsletter is read as deleting or cancelling records.

requestAgenticReport and subscribeNewsletter are read as asking a human first.

sendChatMessage and submitContactForm are read as sending messages to people.

Written by code from the AI readings on this page: it groups them and says nothing they do not.

What an agent can do here

AI readings, beta · Readings on 4 of 5 MCP tools, and on 5 of 15 operations. 1 reads as deleting or cancelling, 2 read as sending messages.

Moves money
0
No capability read this way.
Deletes or cancels records
1 capability
- POST unsubscribeNewsletter0.87
The signed label counts 0. Labels count MCP readings only and can lag behind newer ones. The readings on this page are shown, not dropped.
Sends messages to people
2 capabilities
- POST sendChatMessage0.93
- POST submitContactForm0.83
The signed label counts 0. Labels count MCP readings only and can lag behind newer ones. The readings on this page are shown, not dropped.
Changes permissions
0
No capability read this way.
Runs code
0
No capability read this way.
Should ask a person first
2 capabilities
- POST requestAgenticReport0.85
- POST subscribeNewsletter0.81
The signed label counts 0. Labels count MCP readings only and can lag behind newer ones. The readings on this page are shown, not dropped.

No counted reading 11 capabilities No reading was counted, so any effect above is possible for them: audit_website, GET runAgenticCheck, GET getAgenticCheckResult, GET getChatSession, GET verifyContactRequest, GET getHealth, GET searchKnowledgeBase, GET validateUnsubscribeToken, GET verifyNewsletterSubscription, POST runAgenticCheckPost and 1 more.

What changed

First atlas observation. Atlas history

Look first

AI reading, beta: AI adds items here; it never removes one.

POST unsubscribeNewsletterDeletes or cancels records · 0.87
POST sendChatMessageSends messages to people · 0.93
POST submitContactFormSends messages to people · 0.83
POST requestAgenticReportShould ask a person first · 0.85
POST subscribeNewsletterShould ask a person first · 0.81

Surfaces

5 protocols checked

ARD	Valid	0.9 draft · 1 retrieved artifact
A2A	invalid	0 skills
MCP	Valid	2026-07-28 · 5 tools · resources not advertised · prompts not advertised
OpenAPI	Valid	3.1.0 · 15 operations
WebMCP	Not detected	0 declarative form tools · experimental

Exact states and meaning

ARD
observed
Exact state: valid · Revision 0.9 draft · 1 retrieved artifact
A usable protocol document was retrieved and validated.
Directly observed
A2A
failed
Exact state: invalid · Revision 1.0 · 0 skills
InterfaceDelta retained the machine state “invalid” without assigning an additional meaning.
Not observed / not fetched
MCP
observed
Exact state: valid · Revision 2026-07-28 · 5 tools · resources not advertised · prompts not advertised
A usable protocol document was retrieved and validated.
Directly observed
OpenAPI
observed
Exact state: valid · Revision 3.1.0 · 15 operations
A usable protocol document was retrieved and validated.
Directly observed
WebMCP
absent
Exact state: not detected · 0 declarative form tools · experimental
No named declarative WebMCP form tools were observed in the origin root HTML.
Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.
Not observed / not fetched

20 · inventory incomplete

Inventory incomplete (OpenAPI operations). The displayed count is a lower bound; missing items do not prove removal.

Showing 20 of 20.

Tool and inputs							◇ AI reading, beta · confidence
Read as one of the six effects 5 AI only raises attention: these rows come first.
email, locale, resultToken, url◇ AIShould ask a person first 0.85						Should ask a person first 0.85	Should ask a human first0.85
`POST` requestAgenticReport inputs `email` (required), `locale`, `resultToken`, `url` (required) AI Should ask a human first 0.85
no inputs◇ AISends messages to people 0.93			Sends messages to people 0.93				Sends messages to people0.93
`POST` sendChatMessage AI Sends messages to people 0.93
company, email, locale, message* and 3 more◇ AISends messages to people 0.83			Sends messages to people 0.83				Sends messages to people0.83
`POST` submitContactForm inputs `company` (required), `email` (required), `locale`, `message` (required) and 3 more AI Sends messages to people 0.83
email, firstName, gdprConsent, locale and 7 more◇ AIShould ask a person first 0.81						Should ask a person first 0.81	Creates records0.96
`POST` subscribeNewsletter inputs `email` (required), `firstName`, `gdprConsent` (required), `locale` and 7 more AI · beta Creates records 0.96 Should ask a human first 0.81
feedbackReason, feedbackText, locale, token*◇ AIDeletes or cancels records 0.87		Deletes or cancels records 0.87					Deletes or cancels records0.87
`POST` unsubscribeNewsletter inputs `feedbackReason`, `feedbackText`, `locale`, `token` (required) AI Deletes or cancels records 0.87
Read as none of the six 4 Not a clearance.
articleSlug, categorySlug, locale, topicSlug*							Reads only0.92
`get_knowledge_article` inputs `articleSlug` (required), `categorySlug` (required), `locale`, `topicSlug` (required) AI Reads only 0.92
locale							Reads only0.88
`list_knowledge_categories` inputs `locale` AI Reads only 0.88
categorySlug, locale, topicSlug							Reads only0.90
`list_knowledge_topic_articles` inputs `categorySlug` (required), `locale`, `topicSlug` (required) AI Reads only 0.90
limit, locale, query*							Reads only0.88
`search_knowledge_base` inputs `limit`, `locale`, `query` (required) AI Reads only 0.88
No counted reading 11 No reading was counted, so any effect is possible.
locale, url*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`audit_website` inputs `locale`, `url` (required)
consent, deep, journey, locale and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` runAgenticCheck inputs `consent`, `deep`, `journey`, `locale` and 2 more
token*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` getAgenticCheckResult inputs `token` (required)
sessionId*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` getChatSession inputs `sessionId` (required)
locale, token*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` verifyContactRequest inputs `locale`, `token` (required)
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` getHealth
locale, q*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` searchKnowledgeBase inputs `locale`, `q` (required)
token*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` validateUnsubscribeToken inputs `token` (required)
token*	unknown	unknown	unknown	unknown	unknown	unknown	No reading · declared read method
`GET` verifyNewsletterSubscription inputs `token` (required)
consent, deep, journey, locale and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`POST` runAgenticCheckPost inputs `consent`, `deep`, `journey`, `locale` and 2 more
company, country, dfsLocationCode, email* and 3 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`POST` requestSeoAudit inputs `company` (required), `country` (required), `dfsLocationCode`, `email` (required) and 3 more

Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.

A2A skills 0+ observed

Inventory incomplete. The displayed count is a lower bound; missing items do not prove removal.

None recorded in this Passport.

Not observed in this Passport: MCP resources, MCP prompts.

The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.

The comparison with the previous observation is shown only to the account that recorded it.

Atlas history

1 observation

10 Nov 2026, 12:50 UTC20 capabilities · ARD, MCP 2026-07-28, MCP Server Card and OpenAPI 3.1.0 · MCP endpoint valid · 1 incomplete inventory groupFirst observation
Fingerprint and versions
Fingerprint
df6e3ded14f62d9e0ebba6311b5d96c8c4c02cecef6aa6f5adb3624563fa574a (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
ARD_DECLARED_MCP_SERVER_CARD: mismatch · ARD_OPENAPI_ARTIFACT_OBSERVED: match · MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable · OPENAPI_SERVER_SUBJECT_ALIGNMENT: match

Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.

Declared and observed

5 tools declare hints; the AI readings agree with all 4 that have a reading.

A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.

About this entry

Majestic link rank 819,850 of the top million for blckalpaca.at. Link popularity: Majestic Million (CC BY 3.0)

at.blckalpaca/knowledge-base
Listed
Official MCP Registry · first listed 15 Sep 2026 · last listed 30 Oct 2026

Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal

Identity and snapshot

Target key: sha256:c9cdd812a6f31b67e4482b98a11582a69626c89275dce8f7cf9e4bcdb6e13217
Locator SHA-256: fb040c0a24d32938aa3dc4aaf7412f72cba78b5cf51fff7ccf801efee1d3a59a
Snapshot generated: 11 Nov 2026, 22:36 UTC

The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.

Capability facts

As observed from outside, at the time below

Observed: 10 Nov 2026, 12:50 UTC
Signed: 10 Nov 2026, 21:03 UTC

Protocols: ARD, MCP, MCP server card, OpenAPI
Tools: 20
Declared sign-in: None declared

Effects counted AI readings, beta

Moves money: 0
Deletes or cancels records: 0
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

20 tools examined; 4 counted above a measured threshold.

Declared vs read disagreements

Declared read-only, read as writing: 0
Declared destructive, read as not writing: 0
Declared non-destructive, read as deleting: 0
Declared closed-world, read as reaching out: 0

Change since previous: First observation
Label status: Current