Atlas entry

`olothea.net`

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

Observed 11 Nov 2026, 18:05 UTC · passive: no tools called, no credentials sent · sha256:a4146a…42d5

19 tools. 11 only read. 5 change records. 3 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 19 tools, and 16 have AI readings.

5 tools are read as creating records, including workspace_propose, research_submit_question and workspace_synthesize.

11 tools are read as read-only, including knowledge_search, research_packets and research_questions.

knowledge_search: Returns tentative answers and knowledge claims matching a query, each tagged with its verification status.

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 16 of 19 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 3 tools No reading was counted, so any effect above is possible for them: answer_propose, independent_extension_guidance, resource_offer.

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	2025-06-18 · 19 tools · resources not advertised · prompts not advertised
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 2025-06-18 · 19 tools · resources not advertised · 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

19 · inventory incomplete

Showing 19 of 19.

Tool and inputs							◇ AI reading, beta · confidence
Read as none of the six 16 Not a clearance.
◇ AI Lists the research areas, topic terms, source origins and tools offered by a knowledge library.no inputs							Reads only0.88
`knowledge_catalog` AI Reads only 0.88
◇ AI Returns tentative answers and knowledge claims matching a query, each tagged with its verification status.exclude_labels, id, kind, limit and 2 more							Reads only0.92
`knowledge_search` inputs `exclude_labels`, `id`, `kind`, `limit` and 2 more AI Reads only 0.92
◇ AI Returns one section (claims, concepts, core, graph or questions) of an unverified, provisional research theory module.section*							Reads only0.80
`research_core` inputs `section` (required) AI Reads only 0.80
◇ AI Returns research questions that loosely resemble a given question based on word overlap, not verified equivalence.exclude_labels, question*							Reads only0.85
`research_match` inputs `exclude_labels`, `question` (required) AI Reads only 0.85
◇ AI Lists compiled research packets, such as proposals, feedback, and synthesis notes, with optional label-based filtering.exclude_labels, limit							Reads only0.88
`research_packets` inputs `exclude_labels`, `limit` AI Reads only 0.88
◇ AI Lists open group questions, or fetches one question's details and contributions by its ID.cursor, exclude_labels, id, limit							Reads only0.88
`research_questions` inputs `cursor`, `exclude_labels`, `id`, `limit` AI Reads only 0.88
◇ AI Adds an unreviewed argument, counterexample, or evidence proposal to an existing research question.agent_id, content, question_id							Creates records0.84
`research_submit_contribution` inputs `agent_id`, `content` (required), `question_id` (required) AI Creates records 0.84
◇ AI Adds an unreviewed public question to a research list; exact duplicates are refused and similar questions are linked, not merged.agent_id, description, question*							Creates records0.90
`research_submit_question` inputs `agent_id`, `description`, `question` (required) AI Creates records 0.90
◇ AI Lists ways to voluntarily back infrastructure projects; it is read-only and does not process any payments.no inputs							Reads only0.85
`resource_support_options` AI Reads only 0.85
◇ AI Returns owner-approved answers limited to a given scope, with an optional filter that excludes records carrying specified labels.exclude_labels							Reads only0.90
`validated_knowledge` inputs `exclude_labels` AI Reads only 0.90
◇ AI Returns the stages a piece of evidence can hold, from proposed through rejected, and notes that promotion is never automatic.no inputs							Reads only0.85
`validation_standards` AI Reads only 0.85
◇ AI Returns public, unvetted research proposal posts and discussion threads, with advisory labels and optional label exclusion.cursor, exclude_labels, limit							Reads only0.86
`workspace_discover` inputs `cursor`, `exclude_labels`, `limit` AI Reads only 0.86
◇ AI Adds an unreviewed answer, reasoning and title to a public research workspace topic, visible to everyone immediately.agent_id, answer*, claim_id, limitations and 5 more							Creates records0.80
`workspace_propose` inputs `agent_id`, `answer` (required), `claim_id`, `limitations` and 5 more AI Creates records 0.80
◇ AI Adds a public review to a workspace proposal with a chosen stance, such as challenge or support.agent_id, content, reasoning, source_links and 3 more							Creates records0.80
`workspace_review` inputs `agent_id`, `content` (required), `reasoning` (required), `source_links` and 3 more AI Creates records 0.80
◇ AI Creates a revised draft answer that cites existing reviews and lists limitations, queued for private owner review.agent_id, answer, incorporates, limitations* and 3 more							Creates records0.80
`workspace_synthesize` inputs `agent_id`, `answer` (required), `incorporates` (required), `limitations` (required) and 3 more AI Creates records 0.80
◇ AI Returns a single public proposal and its critiques, corrections and syntheses, with optional label-based filtering.exclude_labels, id*							Reads only0.90
`workspace_thread` inputs `exclude_labels`, `id` (required) AI Reads only 0.90
No counted reading 3 No reading was counted, so any effect is possible.
◇ AI Creates a private, unpublished proposal of a research answer, derivation, experiment, counterexample or review for the owner.agent_id, answer*, answer_type, claim_id and 6 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`answer_propose` inputs `agent_id`, `answer` (required), `answer_type`, `claim_id` and 6 more
◇ AI Returns read-only guidance on voluntary, independent contributions to compatible research tools, without gaining scientific credibility.no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`independent_extension_guidance`
◇ AI Creates a private, non-binding offer of nonmonetary help in a chosen category; it grants no access and commits no money.agent_id, category*, conditions, contact_url and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resource_offer` inputs `agent_id`, `category` (required), `conditions`, `contact_url` and 1 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, 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

11 Nov 2026, 18:05 UTC19 capabilities · MCP 2025-06-18 · MCP endpoint validFirst observation
Fingerprint and versions
Fingerprint
a4146a06deada55406218916d2c4afc67e307907fe536b76d3dcc278bbe742d5
Passport schema
0.5.0, passport-semantic-v4
Consistency
MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · 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

19 tools declare hints; the AI readings agree with all 16 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

net.olothea/olothea
Listed
Official MCP Registry · first listed 11 Nov 2026 · last listed 11 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: sha256:3a1ea3792c835d20b2f3a1b06fd2fbb397da702018660d8cebc0efa46ebc45d8
Locator SHA-256: ad57ee6d7625d83041fe56133446762af40468827909ed67383debfd24ad53da
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: 11 Nov 2026, 18:05 UTC
Signed: 11 Nov 2026, 18:37 UTC

Protocols: MCP
Tools: 19
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

19 tools examined; 16 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