Atlas entry

`crawlcheck.io`

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

Observed 12 Nov 2026, 15:15 UTC · passive: no tools called, no credentials sent · sha256:f626cd…f376

29 capabilities, 28 of them tools. 10 only read. 18 have no reading.

AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (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 28 tools, and 10 have AI readings.

10 tools are read as read-only, including corpus_state, video_site and list_verified_capabilities.

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 10 of 28 MCP tools.

Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
0
No tool read this way.
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.

No counted reading 18 tools No reading was counted, so any effect above is possible for them: best_source, check_site_safety, crawler_path, draft_llms, fix_entitymap, fix_machine_chain, fix_mostly_code, fix_robots, fix_stale_cache, mcp_precheck and 8 more.

What changed

First atlas observation. Atlas history

Look first

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

No tool is read as one of the six effects. A zero is a count, not a clearance.

Surfaces

5 protocols checked

ARD	Valid	v0.91 · 1 retrieved artifact
A2A	invalid	0 skills
MCP	Valid	2025-11-25 · 28 tools · resources not advertised · prompts not advertised
OpenAPI	Observed	0 operations
WebMCP	Observed	1 declarative form tool · experimental

Exact states and meaning

ARD
observed
Exact state: valid · Revision v0.91 · 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 2025-11-25 · 28 tools · resources not advertised · prompts not advertised
A usable protocol document was retrieved and validated.
Directly observed
OpenAPI
observed
Exact state: observed · 0 operations
The protocol surface responded within the passive inspection boundary.
Directly observed
WebMCP
observed
Exact state: observed · 1 declarative form tool · experimental
The origin root HTML, or a followed page, declared WebMCP form tools. InterfaceDelta ran no scripts and submitted no forms.
A declaration does not prove the tool works. WebMCP is an experimental browser capability.
Publisher declared

29 · inventory incomplete

Showing 28 of 28.

Tool and inputs							◇ AI reading, beta · confidence
Read as none of the six 10 Not a clearance.
no inputs							Reads only0.86
`corpus_state` AI Reads only 0.86
code, domain, id, path							Reads only0.85
`explain_finding` inputs `code`, `domain`, `id`, `path` AI Reads only 0.85
domain, field, value*							Reads only0.82
`field_check` inputs `domain` (required), `field` (required), `value` (required) AI Reads only 0.82
domain*, verified_only							Reads only0.87
`list_verified_capabilities` inputs `domain` (required), `verified_only` AI Reads only 0.87
domain, id							Reads only0.90
`machine_record` inputs `domain`, `id` AI Reads only 0.90
domain, shelf							Reads only0.88
`registry_lookup` inputs `domain`, `shelf` AI Reads only 0.88
domain*, path							Reads only0.81
`resolve_robots` inputs `domain` (required), `path` AI Reads only 0.81
no inputs							Reads only0.88
`telemetry` AI Reads only 0.88
handle, id							Reads only0.85
`video_channel` inputs `handle`, `id` AI Reads only 0.85
domain*, handle							Reads only0.80
`video_site` inputs `domain` (required), `handle` AI Reads only 0.80
No counted reading 18 No reading was counted, so any effect is possible.
city, domains, trade	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`best_source` inputs `city`, `domains`, `trade`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`check_site_safety` inputs `domain` (required)
agent, domain*, fresh	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`crawler_path` inputs `agent`, `domain` (required), `fresh`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`draft_llms` inputs `domain` (required)
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`fix_entitymap` inputs `domain` (required)
domain, id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`fix_machine_chain` inputs `domain`, `id`
domain, id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`fix_mostly_code` inputs `domain`, `id`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`fix_robots` inputs `domain` (required)
domain, id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`fix_stale_cache` inputs `domain`, `id`
endpoint, server_name, tools, version	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`mcp_precheck` inputs `endpoint`, `server_name`, `tools`, `version`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`mcp_servers` inputs `domain` (required)
action, agent, domain*, policy and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`preflight` inputs `action`, `agent`, `domain` (required), `policy` and 1 more
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`public_counts`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resolve_domain` inputs `domain` (required)
agent, domain*, path	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resolve_rights` inputs `agent`, `domain` (required), `path`
domain*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`scan_domain` inputs `domain` (required)
lines*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`verify_crawler_log` inputs `lines` (required)
fresh, v*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`video_check` inputs `fresh`, `v` (required)

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.

OpenAPI operations 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

12 Nov 2026, 15:15 UTC29 capabilities · ARD, MCP 2025-11-25, MCP Server Card, OpenAPI and WebMCP · MCP endpoint valid · 1 incomplete inventory groupFirst observation
Fingerprint and versions
Fingerprint
f626cd25af9dd946089bf8abfb8bf61405c64d2294162ef0e8cd0b8c4044f376 (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
ARD_DECLARED_A2A_ARTIFACT: mismatch · ARD_DECLARED_MCP_SERVER_CARD: mismatch · ARD_OPENAPI_ARTIFACT_OBSERVED: indeterminate · 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: indeterminate

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

28 tools declare hints; the AI readings agree with all 10 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

io.github.emmanuelorta/crawlcheck
Listed
Official MCP Registry · first listed 6 Nov 2026 · last listed 6 Nov 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: sha256:70fa79839d55c5e246bde509fcb1a6b80936f77530781ea64d675568cf86c73f
Locator SHA-256: 24eecb0b9f4abd2cad979f8537b77ea7ff9965896fc37f948bc5e77bebe6c7a2
Snapshot generated: 13 Nov 2026, 00:06 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: 12 Nov 2026, 15:15 UTC
Signed: 12 Nov 2026, 17:06 UTC

Protocols: ARD, MCP, MCP server card, OpenAPI, WebMCP
Tools: 29
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

28 tools examined; 10 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