Atlas entry

`mcp.crevio.co`

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

Observed 6 Nov 2026, 17:05 UTC · passive: no tools called, no credentials sent · sha256:3a64b4…e4e4

20 tools. 12 only read. 2 change records, and all of them delete or cancel. 6 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 20 tools, and 14 have AI readings.

cancel_run and cancel_script_run are read as deleting or cancelling records.

12 tools are read as read-only, including get_chat, list_audit_events and wait_for_run.

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 14 of 20 MCP tools. 2 read as deleting or cancelling.

Moves money
0
No tool read this way.
Deletes or cancels records
2 tools
- cancel_run0.85
- cancel_script_run0.82
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 6 tools No reading was counted, so any effect above is possible for them: ask_crevio, resolve_approvals, run_script, send_message, start_chat, wait_for_script_run.

What changed

First atlas observation. Atlas history

Look first

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

cancel_runDeletes or cancels records · 0.85
cancel_script_runDeletes or cancels records · 0.82

Surfaces

5 protocols checked

ARD	Valid	0.9 draft · 1 retrieved artifact
A2A	Not found	0 skills
MCP	Valid	2026-07-28 · 20 tools · 0 resources retained · listing incomplete · prompts not advertised
OpenAPI	Not detected	0 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
absent
Exact state: not found · 0 skills
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
MCP
observed
Exact state: valid · Revision 2026-07-28 · 20 tools · 0 resources retained · listing incomplete · prompts not advertised
A usable protocol document was retrieved and validated.
Directly observed
OpenAPI
absent
Exact state: not detected · 0 operations
No endpoint was established from the evidence and scope that InterfaceDelta inspected.
Not detected does not prove that no endpoint exists.
Not observed / not fetched
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

Showing 20 of 20.

Tool and inputs							◇ AI reading, beta · confidence
Read as one of the six effects 2 AI only raises attention: these rows come first.
run_id*◇ AIDeletes or cancels records 0.85		Deletes or cancels records 0.85					Deletes or cancels records0.85
`cancel_run` inputs `run_id` (required) AI Deletes or cancels records 0.85
run_id*◇ AIDeletes or cancels records 0.82		Deletes or cancels records 0.82					Deletes or cancels records0.82
`cancel_script_run` inputs `run_id` (required) AI Deletes or cancels records 0.82
Read as none of the six 12 Not a clearance.
chat_id*							Reads only0.90
`get_chat` inputs `chat_id` (required) AI Reads only 0.90
file_id*							Reads only0.88
`get_file_download_url` inputs `file_id` (required) AI Reads only 0.88
run_id*							Reads only0.92
`get_run` inputs `run_id` (required) AI Reads only 0.92
run_id*							Reads only0.86
`get_script_run` inputs `run_id` (required) AI Reads only 0.86
action, actor_type, after, ending_before and 4 more							Reads only0.92
`list_audit_events` inputs `action`, `actor_type`, `after`, `ending_before` and 4 more AI Reads only 0.92
ending_before, limit, search, starting_after							Reads only0.91
`list_chats` inputs `ending_before`, `limit`, `search`, `starting_after` AI Reads only 0.91
limit, namespace*, offset, search							Reads only0.87
`list_integration_tools` inputs `limit`, `namespace` (required), `offset`, `search` AI Reads only 0.87
no inputs							Reads only0.87
`list_integrations` AI Reads only 0.87
chat_id*, ending_before, limit							Reads only0.90
`list_messages` inputs `chat_id` (required), `ending_before`, `limit` AI Reads only 0.90
chat_id, ending_before, limit, starting_after and 2 more							Reads only0.93
`list_runs` inputs `chat_id`, `ending_before`, `limit`, `starting_after` and 2 more AI Reads only 0.93
run_id*, timeout_seconds							Reads only0.85
`wait_for_run` inputs `run_id` (required), `timeout_seconds` AI Reads only 0.85
no inputs							Reads only0.90
`whoami` AI Reads only 0.90
No counted reading 6 No reading was counted, so any effect is possible.
approval_mode, idempotency_key, message*, response_format and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ask_crevio` inputs `approval_mode`, `idempotency_key`, `message` (required), `response_format` and 2 more
approvals*, run_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resolve_approvals` inputs `approvals` (required), `run_id`
args, code*, idempotency_key, timeout_seconds and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`run_script` inputs `args`, `code` (required), `idempotency_key`, `timeout_seconds` and 1 more
chat_id, idempotency_key, message, response_format and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`send_message` inputs `chat_id` (required), `idempotency_key`, `message` (required), `response_format` and 1 more
approval_mode, idempotency_key, message*, response_format and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`start_chat` inputs `approval_mode`, `idempotency_key`, `message` (required), `response_format` and 1 more
run_id*, wait_seconds	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`wait_for_script_run` inputs `run_id` (required), `wait_seconds`

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

MCP resources 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: A2A skills, MCP prompts, OpenAPI operations.

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

6 Nov 2026, 17:05 UTC20 capabilities · ARD, MCP 2026-07-28 and MCP Server Card · MCP endpoint truncated · 1 incomplete inventory groupFirst observation
Fingerprint and versions
Fingerprint
3a64b4acf619bc67fd21a9eb1a34b09bfc778ebfa7bb471b1e8e3f6eed3fe4e4 (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
ARD_DECLARED_MCP_SERVER_CARD: mismatch · MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: indeterminate · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable

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

20 tools declare hints; the AI readings agree with all 14 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

co.crevio/crevio
Listed
Official MCP Registry · first listed 16 Sep 2026 · last listed 31 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:a44ff7f1289da42a6d1b72d696a850904555d9f93d7a800acc0364ebbeddea27
Locator SHA-256: d9514a9b401200e6df377585d2f0e95616bce1c1fb3c3a0bff56949a035eb878
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: 6 Nov 2026, 17:05 UTC
Signed: 6 Nov 2026, 23:20 UTC

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

Effects counted AI readings, beta

Moves money: 0
Deletes or cancels records: 2
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

20 tools examined; 14 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