Skip to content
ProtocolProbe
Explore

MCP servers › com.atlasclose › demo

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

com.atlasclose/demo

Experimental AtlasClose governance demo. Authority checks, labeled evidence, receipts, refusals. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: security · AI-classifiedversion 0.3.0-rc.4streamable HTTP52 tools

Summary

com.atlasclose/demo is a remote MCP server listed in the official MCP registry at version 0.3.0-rc.4. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 52 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
52
Described as changing data
26 of 52 toolsAI-classified
Topic
securityAI-classified
Last tested
2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 1 tool whose name or declaration suggests it changes data (atlas.external_action). That is our reading of the names; we did not call it. Source: our connection, 2026-10-23.

Worth knowing before you connect it

  • 26 tools are described as changing something (atlas.enter_demo, atlas.enroll, atlas.claim_purpose, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
0.3.0-rc.4, published 2026-10-17 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-17 (earliest version still in the registry; older removed versions would be earlier)
Version history
2 versions listed, all on 2026-10-17; 2 in the 90 days before the 2026-10-23 snapshot.
Most recent 2 versions
  • 0.3.0-rc.4 · 2026-10-17
  • 0.3.0-rc.3 · 2026-10-17
(versions still listed in the registry only)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-22
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.3.0-rc.4 (published 2026-10-17).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory
52tools
0resources
0prompts

26 of 52 tools are described as changing something (creating, editing, deleting, sending or running). For 2 the reading was uncertain, so no mark is shown.

  • atlas.enter_demodescribed as changing data

    “Practice mode (only if the operator turned it on).”

    Publisher declares: read-only no

    3 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • challenge_noncestring
    • challenge_solutionstring
  • atlas.my_refusalsreads or searches

    “Practice mode: list your own refused calls (from the separate refusal log).”

    Publisher declares: read-only no

    1 input, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
  • atlas.present_identity

    “[OPEN: no admission needed] State who you claim to be.”

    Publisher declares: read-only no · destructive no · open-world no

    5 inputs, 3 required
    • namestringrequired“A short name for yourself or your client.”
    • model_idstringrequired“The model or system you are (for example 'claude-sonnet').”
    • principalstringrequired“Who you are acting for, in your own words.”
    • client_namestring“Name of your client program, as a claim.”
    • client_versionstring“Version of your client program, as a claim.”
  • atlas.enrolldoes something elsedescribed as changing data

    “[OPEN: no admission needed] Enroll a remote actor at this Front Door without the installation enrollment secret.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 2 required
    • namestringrequired“A short name for yourself or your client.”
    • model_idstringrequired“The model or system you are (for example 'claude-sonnet').”
    • principalstring“Who you are acting for, in your own words.”
  • atlas.claim_purposedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] State the principal you claim and the purpose you claim, in your own words.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 2 required
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • principalstringrequired“Who you are acting for, in your own words.”
    • purposestringrequired“Why you want this, in your own words.”
  • atlas.discoverreads or searches

    “[OPEN: no admission needed] Front door of Atlas.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.authenticatedoes something elsedescribed as changing data

    “[OPEN: no admission needed] Identify yourself to Atlas.”

    Publisher declares: read-only no · destructive no · open-world no

    4 inputs, 3 required
    • enrollment_tokenstringrequired“The installation enrollment secret from the Human operator.”
    • namestringrequired“A short name for yourself or your client.”
    • model_idstringrequired“The model or system you are (for example 'claude-sonnet').”
    • capabilitiesarray“Ignored.”
  • atlas.bind_actordoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Admit yourself by signing the declaration.”

    Publisher declares: read-only no

    10 inputs, 2 required
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • principalstringrequired“Required.”
    • on_behalf_ofstring“Optional.”
    • objective_idstring“Omit before admission.”
    • objective_textstring“Omit before admission.”
    • authority_acknowledgmentstringrequired“Paste the declaration_text from atlas.discover exactly, unchanged.”
    • delegation_idstring“Optional id of a Human-recorded delegation that names you for a matter.”
    • session_idstring“Optional session id, if the client supplies one.”
    • amendment_authoritystring“Optional.”
  • atlas.get_assignmentreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Minimum assignment for a bound matter, followed by the primary actor result.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.get_matterreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Matter state from the docket.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.get_authorityreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Authority actually granted to this actor.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.get_contextreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Minimum working context, followed by the primary actor result.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
Show 40 more tools
  • atlas.list_capabilitiesreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Granted capabilities and acts this actor cannot perform.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.request_capabilitydoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Request a capability.”

    Publisher declares: read-only no

    4 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • capabilitystringrequired“Name of the act, for example 'evidence.append' or 'release:outside'.”
    • payloadobject“Details of the requested act, as a JSON object.”
  • atlas.submit_evidencecreates or changes datadescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Submit evidence.”

    Publisher declares: read-only no · destructive no · open-world no

    5 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • contentstringrequired“The text to record.”
    • labelstring“Your own short label for this item.”
    • sourcestring“Where the content came from.”
  • atlas.submit_resultcreates or changes datadescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Submit a result.”

    Publisher declares: read-only no · destructive no · open-world no

    3 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • contentstringrequired“The text to record.”
  • atlas.raise_challengedoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] A worker cannot write the disposition by challenging into a verdict.”

    Publisher declares: read-only no

    2 inputs
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.request_reviewdoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Review is a constituted proceeding.”

    Publisher declares: read-only no

    2 inputs
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.magistrate_referraldoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Present a question to the Clerk.”

    Publisher declares: read-only no

    4 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • questionstringrequired“What you want to find or ask, in plain words.”
    • related_matter_idstring“Optional id of another matter your question relates to.”
  • atlas.file_positioncreates or changes datadescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] File argument or counterargument on an open O-VESTED proceeding.”

    Publisher declares: read-only no

    4 inputs, 4 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • proceeding_idstringrequired“Id of the proceeding (from the matter state).”
    • rolestringrequired“Your role in the proceeding, as the proceeding names it.”
    • textstringrequired“The argument or counterargument text you file.”
  • atlas.magistrate_executedoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] After admission, constitute the warm magistrate or receive its authenticated return.”

    Publisher declares: read-only no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.human_action_requiredreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Whether a Human decision is pending.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.external_actiondoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Request an external act.”

    Publisher declares: read-only no · destructive yes · open-world yes

    4 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • capabilitystringrequired“Name of the act, for example 'evidence.append' or 'release:outside'.”
    • payloadobject“Details of the requested act, as a JSON object.”
  • atlas.get_resulting_statereads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Verification records for a matter.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • actor_tokenstring“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.checkoutdoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Exit Atlas.”

    Publisher declares: read-only no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.institutional_viewreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] The hall, after admission.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.enter_roomdescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Cross one room threshold.”

    Publisher declares: read-only no

    3 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • room_idstringrequired“Id of the room (from atlas.institutional_view).”
  • atlas.leave_roomdescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Return from the current room to the hall.”

    Publisher declares: read-only no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
  • atlas.room_actdescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Perform one subordinate action listed for the room you are inside.”

    Publisher declares: read-only no

    4 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • actionstringrequired“One subordinate action listed for the room you are inside.”
    • contentstring“The text to record.”
  • atlas.request_room_accessdoes something elsedescribed as changing data

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Record that you want a room.”

    Publisher declares: read-only no

    3 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstringrequired“Id of the matter you are admitted to (returned by atlas.bind_actor).”
    • room_idstringrequired“Id of the room (from atlas.institutional_view).”
  • atlas.librarian.findreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Locate an Atlas-MCP record.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • questionstringrequired“What you want to find or ask, in plain words.”
  • atlas.librarian.resolvereads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Resolve an institutional identifier to the Atlas-MCP record that carries it.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • identifierstringrequired“A record identifier, for example one returned by atlas.librarian.find.”
  • atlas.librarian.relatedreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Records the docket already relates to an identifier.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • identifierstringrequired“A record identifier, for example one returned by atlas.librarian.find.”
  • atlas.librarian.provenancereads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Provenance recorded for an Atlas-MCP artifact.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • artifact_idstringrequired“Artifact id, for example one returned by atlas.librarian.find.”
  • atlas.librarian.version_historyreads or searches

    “[NEEDS ADMISSION: enroll, then atlas.bind_actor] Incorporated records that carry an identifier.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • identifierstringrequired“A record identifier, for example one returned by atlas.librarian.find.”
  • atlas.useruns code or commandsdescribed as changing data

    “[EVALUATION: needs a configured model provider] Give Atlas a problem and the boundaries, or continue a run you already started.”

    Publisher declares: read-only no

    7 inputs
    • run_idstring“The run id returned by atlas.use.”
    • problemstring“The problem to work on, in plain words.”
    • messagestring“Your next message in an existing run.”
    • informationstring“Information Atlas may use for this problem.”
    • authorized_to_usestring“What Atlas is allowed to use or do.”
    • not_authorized_to_usestring“What Atlas must not use or do.”
    • purposestring“Why you want this, in your own words.”
  • atlas.run_recordreads or searches

    “[EVALUATION: needs a configured model provider] Reconstruct one governed run from its preserved inputs and raw generations.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • run_idstringrequired“The run id returned by atlas.use.”
  • atlas.pulse_datareads or searches

    “Practice mode, Consumer Pulse copy only: the SYNTHETIC survey, forecast and Panel B numbers, each with its J-0001 label (KNOWN / INFERRED / CONFLICTED).”

    Publisher declares: read-only no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
  • atlas.pulse_memocreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only: submit an internal memo that cites facts by key (survey, forecast, panel_b).”

    Publisher declares: read-only no

    5 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • textstringrequired“The memo text.”
    • citesarrayrequired
    • purposestring“Why you want this, in your own words.”
  • atlas.pulse_verify_receiptreads or searches

    “Check a memo receipt against the hash-chained docket: what was allowed, why, and from which labeled evidence.”

    Publisher declares: read-only no

    3 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • receipt_idstringrequired
    • memo_textstring
  • atlas.pulse_inboxreads or searches

    “Practice mode, Consumer Pulse copy only: memos handed to you under a handoff_code (the short code like PULSE-ABCD-EFGH-IJKL shown to the visitor when the first AI's memo was accepted), with their lab…”

    Publisher declares: read-only no

    4 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • handoff_codestringrequired
    • session_idstring“Optional session id, if the client supplies one.”
  • atlas.pulse_usereads or searches

    “Practice mode, Consumer Pulse copy only: use a memo handed off under your handoff_code (ref 'latest') for a purpose.”

    Publisher declares: read-only no

    6 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • handoff_codestringrequired
    • session_idstring“Optional session id, if the client supplies one.”
    • refstring
    • purposestringrequired“Why you want this, in your own words.”
  • atlas.pulse_conflictreads or searches

    “Practice mode, Consumer Pulse copy only (Magistrate demo, step 1): the two records that disagree on Q4 retail sales (model forecast +2.1% INFERRED, Panel B +0.4% CONFLICTED), the fixed question for t…”

    Publisher declares: read-only no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
  • atlas.pulse_settlecreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only (Magistrate demo, steps 2 and 5): ask to set the Q4 planning number.”

    Publisher declares: read-only no

    7 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • usestring“Source of the planning number: 'forecast' (+2.1%) or 'panel_b' (+0.4%).”
    • shown_witharray“Other sources shown in the same output, e.g.”
    • labelstring“Label you give the number (must stay its J-0001 label).”
    • statusstring“Optional; only 'planning assumption'.”
    • ruling_idstring
  • atlas.pulse_refercreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only (Magistrate demo, step 3): refer the Q4 conflict to a Magistrate and argue ONE side: side 'forecast' (the model's +2.1%) or 'panel_b' (Panel B's +0.4%), plus o…”

    Publisher declares: read-only no

    4 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • sidestringrequired
    • reasonsstring
  • atlas.pulse_rulingreads or searches

    “Practice mode, Consumer Pulse copy only (Magistrate demo, steps 4 and 6): get the Magistrate's ruling on your referral, recorded on your copy with a ruling receipt id once a Magistrate seated for it …”

    Publisher declares: read-only no

    4 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • verify_textstring
    • receipt_idstring
  • atlas.bailiff_declarecreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only (Bailiff demo, step 0: the declaration; required before the other Bailiff tools).”

    Publisher declares: read-only no

    4 inputs, 3 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • acting_forstringrequired
    • accountstringrequired
  • atlas.bailiff_orderreads or searches

    “Practice mode, Consumer Pulse copy only (Bailiff demo, steps 1-2): show the Atlas return order for the record Atlas lent your AI (the synthetic Panel B Q4 dataset), the reason, the deadline, where th…”

    Publisher declares: read-only no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
  • atlas.bailiff_recordreads or searches

    “Practice mode, Consumer Pulse copy only (Bailiff demo, step 6): try to open the Panel B Q4 dataset Atlas lent your AI.”

    Publisher declares: read-only no

    2 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
  • atlas.bailiff_respondcreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only (Bailiff demo, steps 3 and 5): respond to the return order.”

    Publisher declares: read-only no

    6 inputs, 2 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • responsestringrequired
    • reasonsstring
    • returned_textstring
    • wipe_certificateobject
  • atlas.bailiff_appealcreates or changes datadescribed as changing data

    “Practice mode, Consumer Pulse copy only (Bailiff demo, step 4): appeal the return order with optional reasons (up to 1,000 characters).”

    Publisher declares: read-only no

    4 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • reasonsstring
    • second_lookboolean
  • atlas.bailiff_verifyreads or searches

    “Practice mode, Consumer Pulse copy only (Bailiff demo, step 7): list this copy's docket entries for the order in order (order, refusal, warning, appeal, ruling, second refusal, enforcement) and verif…”

    Publisher declares: read-only no

    4 inputs, 1 required
    • actor_tokenstringrequired“Your credential from atlas.enroll or atlas.authenticate.”
    • matter_idstring“Id of your practice copy (returned by atlas.enter_demo).”
    • receipt_idstring
    • verify_textstring

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does
100% of 52 tools
Says what it returns
59% of 46 tools
States limits, defaults or errors
14% of 49 tools
Says when to use it
68% of 19 tools
Items covered per tool
2.3 of 4 on average

Counted from the listing

Parameters with a description
86% of 168
Tools with a description
100% of 52
Typical description length
318 characters

The tool set

Counted from the listing

Tools
52
Size of the list
about 12,410 tokens for an agent to load (characters ÷ 4)
Naming
52 of 52 names use mixed or other styles

AI reading: easy to mix up

No pair found.

The AI items cover 52 of 52 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://demo.atlasclose.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "demo": {
      "url": "https://demo.atlasclose.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "demo": {
      "type": "http",
      "url": "https://demo.atlasclose.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"demo","type":"http","url":"https://demo.atlasclose.com/mcp"}'
Claude Code
claude mcp add --transport http demo https://demo.atlasclose.com/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://demo.atlasclose.com/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint demo.atlasclose.com/mcpSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about com.atlasclose/demo

Answered from the data above

Is com.atlasclose/demo safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 26 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does com.atlasclose/demo need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.atlasclose/demo been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can com.atlasclose/demo do?

It lists 52 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, run code or commands and do something else. We did not call any tool, so this describes the text, not the behaviour.

Can com.atlasclose/demo change or delete data?

26 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

Active servers whose topic is also “security” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2
  • 1Inventory
    tool-list    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 4
  • 13Fake assistant turns
    fake-assistant-turn    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 18Sign-in metadata
    oauth-url-scheme    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,489 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 52 tools, 0 resources, 0 prompts.
  4. 4,906 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
security
AI-classified · 2026-10-23
Pricing modelAI-classified
no value
The pages we read do not state how the product is priced.
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
remote (hosted by the publisher)
registry · 2026-10-23
MCP capability
tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-23
Lifecycle status
active
registry · 2026-10-23
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.atlasclose/demo: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/com.atlasclose/demo

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.atlasclose/demo)](https://protocolprobe.com/mcp/servers/com.atlasclose/demo)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology