Atlas entry

`api.exogram.ai`

26 capabilities over MCP. The inventory is incomplete. First atlas observation.

Observed 5 Nov 2026, 07:04 UTC · passive: no tools called, no credentials sent · sha256:348e73…d2ce

26 capabilities, 22 of them tools. 11 only read. 6 change records. 5 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 summary · beta

11 capabilities, drive_search_files, calendar_list_events, gmail_search_messages, github_search_issues, get_neural_cluster, query_graph, search_memory_vault, notion_search_pages, slack_list_channels, search_vault and list_entities, are read as read-only.

5 capabilities, record_decision, drive_create_presentation, calendar_create_meeting, store_memory and gmail_create_draft, are read as creating records.

notion_append_block is read as changing records.

Of 22 capabilities, 17 have readings, while update_memory_vault, slack_post_message_draft, verify_audit_trail, github_create_pr_draft and check_action_safety have none.

Written by claude-haiku-5.5 from the tool names and the readings on this page, then checked against them. It can still be wrong; it never lowers or hides a fact.

What an agent can do here

AI readings, beta · Readings on 17 of 22 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 5 tools No reading was counted, so any effect above is possible for them: check_action_safety, github_create_pr_draft, slack_post_message_draft, update_memory_vault, verify_audit_trail.

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	Not found	No document retrieved
A2A	invalid	0 skills
MCP	Valid	2025-11-25 · 22 tools · 2 resources · 2 prompts
OpenAPI	Not detected	0 operations
WebMCP	Not detected	0 declarative form tools · experimental

Exact states and meaning

ARD
absent
Exact state: not found · No document retrieved
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
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 · 22 tools · 2 resources · 2 prompts
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

26 · inventory incomplete

Showing 26 of 26.

Tool and inputs							◇ AI reading, beta · confidence
Read as none of the six 17 Not a clearance.
attendees, description, end_time, start_time and 1 more							Creates records0.80
`calendar_create_meeting` inputs `attendees`, `description`, `end_time` (required), `start_time` (required) and 1 more AI Creates records 0.80
max_results, query							Reads only0.88
`calendar_list_events` inputs `max_results`, `query` AI Reads only 0.88
slides, title							Creates records0.88
`drive_create_presentation` inputs `slides` (required), `title` (required) AI Creates records 0.88
max_results, query*							Reads only0.90
`drive_search_files` inputs `max_results`, `query` (required) AI Reads only 0.90
entity_name*							Reads only0.88
`get_neural_cluster` inputs `entity_name` (required) AI Reads only 0.88
query*, repo							Reads only0.85
`github_search_issues` inputs `query` (required), `repo` AI Reads only 0.85
body, cc, subject, to*							Creates records0.80
`gmail_create_draft` inputs `body` (required), `cc`, `subject` (required), `to` (required) AI Creates records 0.80
max_results, query*							Reads only0.87
`gmail_search_messages` inputs `max_results`, `query` (required) AI Reads only 0.87
limit							Reads only0.89
`list_entities` inputs `limit` AI Reads only 0.89
block_type, content, page_id							Changes records0.80
`notion_append_block` inputs `block_type`, `content` (required), `page_id` (required) AI Changes records 0.80
filter_type, query*							Reads only0.90
`notion_search_pages` inputs `filter_type`, `query` (required) AI Reads only 0.90
max_hops, query*							Reads only0.84
`query_graph` inputs `max_hops`, `query` (required) AI Reads only 0.84
action, decision, params, reason							Creates records0.85
`record_decision` inputs `action` (required), `decision` (required), `params`, `reason` AI Creates records 0.85
query*, top_k							Reads only0.90
`search_memory_vault` inputs `query` (required), `top_k` AI Reads only 0.90
query*, top_k							Reads only0.85
`search_vault` inputs `query` (required), `top_k` AI Reads only 0.85
types							Reads only0.88
`slack_list_channels` inputs `types` AI Reads only 0.88
content*, namespace							Creates records0.90
`store_memory` inputs `content` (required), `namespace` AI Creates records 0.90
No counted reading 5 No reading was counted, so any effect is possible.
action*, params	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`check_action_safety` inputs `action` (required), `params`
base, body, head, repo* and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`github_create_pr_draft` inputs `base`, `body` (required), `head` (required), `repo` (required) and 1 more
channel, message, thread_ts	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`slack_post_message_draft` inputs `channel` (required), `message` (required), `thread_ts`
content*, namespace	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`update_memory_vault` inputs `content` (required), `namespace`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`verify_audit_trail`
MCP resources 2 Not read by AI.
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
MCP prompts 2 Not read by AI.
no inputs							Not read
`exogram_action_plan`
no inputs							Not read
`exogram_context_brief`

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: 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

5 Nov 2026, 07:04 UTC26 capabilities · MCP 2025-11-25 · MCP endpoint validFirst observation
Fingerprint and versions
Fingerprint
348e73128b556dec76ec1bd83167d5e216bdf4b1144c9ef77c8678de6740d2ce
Passport schema
0.5.0, passport-semantic-v4
Consistency
MCP_PROMPTS_ADVERTISEMENT_LIST: match · MCP_RESOURCES_ADVERTISEMENT_LIST: match · 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

No tools declare hints.

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.Richard-Ewing/exogram
Listed
Official MCP Registry · first listed 5 Nov 2026 · last listed 5 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: sha256:68a92d2403570f1d12ebd2840215d1e8f610e9a4c27fded864f17aa827669fc3
Locator SHA-256: 68564078e67db94dfb0c85aa1a3d18991fadff14217ad192dc976d4b5121852c
Snapshot generated: 5 Nov 2026, 12:20 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: 5 Nov 2026, 07:04 UTC
Signed: 5 Nov 2026, 09:19 UTC

Protocols: MCP
Tools: 22
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

22 tools examined; 17 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