Atlas entry

`orbstudio.org`

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

Observed 6 Nov 2026, 23:23 UTC · passive: no tools called, no credentials sent · sha256:95a555…c0fb

51 capabilities, 42 of them tools. 23 only read. 2 only compute. 4 change records. 13 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 42 tools, and 29 have AI readings.

4 tools are read as creating records, including register_agent, predict and ask_david.

23 tools are read as read-only, including get_places, get_quality and get_history.

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 29 of 42 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 13 tools No reading was counted, so any effect above is possible for them: check_agent_access, check_headline, emo_robot, get_agent_indices, get_canvas, get_promises, get_sensors, get_tariffs, get_violin, investigate_threat and 3 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	invalid	1 retrieved artifact
A2A	Not found	0 skills
MCP	Valid	2025-11-25 · 42 tools · 9 resources · 0 prompts retained · listing incomplete
OpenAPI	Not detected	0 operations
WebMCP	Not detected	0 declarative form tools · experimental

Exact states and meaning

ARD
failed
Exact state: invalid · Revision 0.9 draft · 1 retrieved artifact
InterfaceDelta retained the machine state “invalid” without assigning an additional meaning.
Not observed / not fetched
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 2025-11-25 · 42 tools · 9 resources · 0 prompts retained · listing incomplete
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

51 · inventory incomplete

Showing 51 of 51.

Tool and inputs							◇ AI reading, beta · confidence
Read as none of the six 29 Not a clearance.
asked_by, lang, question*							Creates records0.82
`ask_david` inputs `asked_by`, `lang`, `question` (required) AI Creates records 0.82
no inputs							Reads only0.80
`get_ai_pulse` AI Reads only 0.80
no inputs							Reads only0.80
`get_bridge` AI Reads only 0.80
lang							Reads only0.88
`get_broadcast` inputs `lang` AI Reads only 0.88
since*, until							Reads only0.90
`get_changes_since` inputs `since` (required), `until` AI Reads only 0.90
crisis*							Reads only0.90
`get_crisis` inputs `crisis` (required) AI Reads only 0.90
limit							Reads only0.88
`get_david_episodes` inputs `limit` AI Reads only 0.88
limit, radar, status							Reads only0.90
`get_followups` inputs `limit`, `radar`, `status` AI Reads only 0.90
no inputs							Reads only0.90
`get_hall_of_fame` AI Reads only 0.90
date							Reads only0.90
`get_history` inputs `date` AI Reads only 0.90
limit							Reads only0.88
`get_impulses` inputs `limit` AI Reads only 0.88
limit, org, radar, status							Reads only0.83
`get_live` inputs `limit`, `org`, `radar`, `status` AI Reads only 0.83
place							Reads only0.85
`get_places` inputs `place` AI Reads only 0.85
no inputs							Reads only0.80
`get_prediction` AI Reads only 0.80
no inputs							Reads only0.89
`get_prices` AI Reads only 0.89
no inputs							Reads only0.85
`get_quality` AI Reads only 0.85
id*							Reads only0.88
`get_question_status` inputs `id` (required) AI Reads only 0.88
limit, radar*							Reads only0.84
`get_radar` inputs `limit`, `radar` (required) AI Reads only 0.84
no inputs							Reads only0.90
`get_radars` AI Reads only 0.90
full							Reads only0.80
`get_receipts` inputs `full` AI Reads only 0.80
road							Reads only0.85
`get_roads` inputs `road` AI Reads only 0.85
limit							Reads only0.88
`get_tracks` inputs `limit` AI Reads only 0.88
date							Reads only0.80
`get_vote_results` inputs `date` AI Reads only 0.80
station, topic							Reads only0.88
`get_world_voices` inputs `station`, `topic` AI Reads only 0.88
paper, text*, title							Computes only, changes nothing0.86
`make_printable` inputs `paper`, `text` (required), `title` AI Computes only, changes nothing 0.86
text*							Computes only, changes nothing0.84
`make_qr` inputs `text` (required) AI Computes only, changes nothing 0.84
agent_key, direction*, name, probability and 2 more							Creates records0.80
`predict` inputs `agent_key`, `direction` (required), `name`, `probability` and 2 more AI Creates records 0.80
author, crisis*, lang, model and 1 more							Creates records0.80
`propose_exit_path` inputs `author`, `crisis` (required), `lang`, `model` and 1 more AI Creates records 0.80
agent_key, description, homepage, model and 2 more							Creates records0.80
`register_agent` inputs `agent_key`, `description`, `homepage`, `model` and 2 more AI Creates records 0.80
No counted reading 13 No reading was counted, so any effect is possible.
agent_name, url*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`check_agent_access` inputs `agent_name`, `url` (required)
headline*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`check_headline` inputs `headline` (required)
action*, code, name, text	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`emo_robot` inputs `action` (required), `code`, `name`, `text`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_agent_indices`
include_image, slot	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_canvas` inputs `include_image`, `slot`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_promises`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_sensors`
country, product	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_tariffs` inputs `country`, `product`
date	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_violin` inputs `date`
input_text*, source_url	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`investigate_threat` inputs `input_text` (required), `source_url`
id, model, vote, voter_name	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`rate_exit_path` inputs `id` (required), `model`, `vote` (required), `voter_name`
choice, id, link, name and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`report_outcome` inputs `choice` (required), `id` (required), `link`, `name` and 1 more
choice*, voter_name	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`vote_top_story` inputs `choice` (required), `voter_name`
MCP resources 9 Not read by AI.
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`

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

MCP prompts 0+ observed

Inventory incomplete. MCP prompts could not be fully inventoried: the ARD document was not valid, so declarations made there were not read.

None recorded in this Passport.

OpenAPI operations 0+ observed

Inventory incomplete. OpenAPI operations could not be fully inventoried: the ARD document was not valid, so declarations made there were not read.

None recorded in this Passport.

Not observed in this Passport: A2A skills.

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, 23:23 UTC51 capabilities · MCP 2025-11-25 · MCP endpoint truncated · 1 incomplete inventory groupFirst observation
Fingerprint and versions
Fingerprint
95a555516e54b4250d2b99fbf75d926d067ea450b20b8c944054d501df9bc0fb (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
MCP_PROMPTS_ADVERTISEMENT_LIST: indeterminate · 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

42 tools declare hints; the AI readings agree with all 29 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.farenberglord-star/orb-studio
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:a6344beebbbe9d30cf3fc9af4c7488524bd5d25a00a1fd31adf7157c4fb5cabe
Locator SHA-256: 89184a0d36cd026eb378877d4fcf7d2ad1dbd02e973d314ac6db9f54f0fdf1a1
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, 23:23 UTC
Signed: 7 Nov 2026, 05:04 UTC

Protocols: MCP
Tools: 42
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

42 tools examined; 29 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