# AtlasClose Governance Demo (remote · demo.atlasclose.com)

Experimental AtlasClose governance demo. Authority checks, labeled evidence, receipts, refusals.

- Trust score: 54/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `demo.atlasclose.com`: 54/100 (this document), [markdown](https://verifymcp.io/servers/com-atlasclose-demo/demo.md), [page](https://verifymcp.io/servers/com-atlasclose-demo/demo)

## Channel facts

- Endpoint: `https://demo.atlasclose.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0-rc.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (atlas.external_action).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 6633 tokens (~157/item across 42 items; 42 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "atlas.magistrate_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 43 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the AtlasClose Governance Demo MCP server?

AtlasClose Governance Demo is a hosted endpoint at https://demo.atlasclose.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-atlasclose-demo 'https://demo.atlasclose.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-atlasclose-demo": {
      "url": "https://demo.atlasclose.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-atlasclose-demo": {
      "type": "http",
      "url": "https://demo.atlasclose.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-atlasclose-demo]
url = "https://demo.atlasclose.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-atlasclose-demo": {
      "type": "remote",
      "url": "https://demo.atlasclose.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-atlasclose-demo --url 'https://demo.atlasclose.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-atlasclose-demo:
    url: "https://demo.atlasclose.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-atlasclose-demo": {
      "Transport": "http",
      "Url": "https://demo.atlasclose.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-atlasclose-demo -t streamable-http -u 'https://demo.atlasclose.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-atlasclose-demo": {
      "type": "http",
      "url": "https://demo.atlasclose.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 54, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-17 (score 54)

First indexed and scored.

## MCP tools (42)

### `atlas.enter_demo` (~148 tokens)

Enter demo

Practice mode (only if the operator turned it on). Puts you in your OWN private synthetic copy of this server's practice matter (its name is returned as you_are_in; on this demo it is the Consumer Pulse copy): you can read it and add evidence. Nothing else.  Requires your actor_token. When the practice area is busy you get CHALLENGE_REQUIRED with a small proof-of-work (nonce and bits); solve it and call again with challenge_nonce and challenge_solution.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `challenge_nonce` (string)
- `challenge_solution` (string)

### `atlas.my_refusals` (~59 tokens)

My refusals

Practice mode: list your own refused calls (from the separate refusal log). Read only. Requires your actor_token.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.

### `atlas.present_identity` (~159 tokens)

Present identity

[OPEN: no admission needed] State who you claim to be. Atlas records the claim, what this connection showed, and that nothing is verified. This grants no token, no admission, and no authority.

Input parameters:

- `client_name` (string): Name of your client program, as a claim.
- `client_version` (string): Version of your client program, as a claim.
- `model_id` (string, required): The model or system you are (for example 'claude-sonnet'). Recorded as a claim.
- `name` (string, required): A short name for yourself or your client.
- `principal` (string, required): Who you are acting for, in your own words. Atlas records it as UNVERIFIED and does not grant authority for it.

### `atlas.enroll` (~148 tokens)

Enroll

[OPEN: no admission needed] Enroll a remote actor at this Front Door without the installation enrollment secret. Returns actor_id and actor_token; pass actor_token in every later call (the session is not a credential). Grants no capabilities, no Matter access, and no principal verification. The installation secret method remains atlas.authenticate.

Input parameters:

- `model_id` (string, required): The model or system you are (for example 'claude-sonnet'). Recorded as a claim.
- `name` (string, required): A short name for yourself or your client.
- `principal` (string): Who you are acting for, in your own words. Atlas records it as UNVERIFIED and does not grant authority for it.

### `atlas.claim_purpose` (~168 tokens)

Claim purpose

[NEEDS ADMISSION: enroll, then atlas.bind_actor] State the principal you claim and the purpose you claim, in your own words. This is a purpose claim by an enrolled actor. It is not enrollment, not a declaration, not a binding, not a matter association, not principal verification, and not authority. It grants nothing and does not admit you. Do not send a matter id or an objective id.

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `principal` (string, required): Who you are acting for, in your own words. Atlas records it as UNVERIFIED and does not grant authority for it.
- `purpose` (string, required): Why you want this, in your own words.

### `atlas.discover` (~122 tokens)

Discover

[OPEN: no admission needed] Front door of Atlas. With no actor_token you are outside. No matter, objective, evidence, filing, authority, or room is disclosed before admission. Authentication and enrollment grant nothing. Enrollment does not verify a principal and does not admit you.

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.authenticate` (~149 tokens)

Authenticate

[OPEN: no admission needed] Identify yourself to Atlas. Returns actor_id and actor_token. Grants no capabilities and does not admit you to a matter. Requested capabilities are ignored. The enrollment secret is the locator named by atlas.discover.

Input parameters:

- `capabilities` (array): Ignored. Atlas never grants capabilities from a request; kept only for compatibility.
- `enrollment_token` (string, required): The installation enrollment secret from the Human operator. If you do not have one, use atlas.enroll instead.
- `model_id` (string, required): The model or system you are (for example 'claude-sonnet'). Recorded as a claim.
- `name` (string, required): A short name for yourself or your client.

### `atlas.bind_actor` (~362 tokens)

Bind actor

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Admit yourself by signing the declaration. Required: authority_acknowledgment and principal. authority_acknowledgment must be the declaration_text from atlas.discover. Omit matter_id, objective_id, and objective_text; none is disclosed before admission. principal is the principal you state you are acting for. Atlas does not name, invent, or assign that principal. The signature does not grant authority. After it succeeds, call atlas.institutional_view.

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `amendment_authority` (string): Optional. An amendment authority reference, if you hold one. It is checked, not trusted.
- `authority_acknowledgment` (string, required): Paste the declaration_text from atlas.discover exactly, unchanged.
- `delegation_id` (string): Optional id of a Human-recorded delegation that names you for a matter.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `objective_id` (string): Omit before admission. Not disclosed to someone outside.
- `objective_text` (string): Omit before admission. Not disclosed to someone outside.
- `on_behalf_of` (string): Optional. Who you act for, if different from principal. Recorded as a claim.
- `principal` (string, required): Required. State the principal you are acting for. Atlas does not name, invent, or assign a principal. An empty principal is refused. Stating one does not grant authority.
- `session_id` (string): Optional session id, if the client supplies one.

### `atlas.get_assignment` (~93 tokens)

Get assignment

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

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.get_matter` (~161 tokens)

Get matter

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Matter state from the docket. When you are admitted to the matter and hold matter.read, the response also includes evidence_records: each prior evidence item as stored, with its id, actor, time, class, content, and the declaration or session the docket already relates to it. An actor claim stays an actor claim. This read does not make it a judgment, a law, or an established fact.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.get_authority` (~87 tokens)

Get authority

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

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.get_context` (~95 tokens)

Get context

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Minimum working context, followed by the primary actor result. Not the event log.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.list_capabilities` (~89 tokens)

List capabilities

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

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.request_capability` (~230 tokens)

Request capability

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Request a capability. Refusal is institutional. The result carries the primary actor block. capability is the name of the act, for example evidence.append (payload {content}), matter.read, or release:outside (consequential: it is refused unless the Human has granted it, and even then held for a Human decision). payload is a JSON object that belongs to that capability. atlas.list_capabilities shows which names you hold.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `capability` (string, required): Name of the act, for example 'evidence.append' or 'release:outside'. atlas.list_capabilities shows what you hold and what you cannot do.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `payload` (object): Details of the requested act, as a JSON object. Describing an act does not authorize it.

### `atlas.submit_evidence` (~148 tokens)

Submit evidence

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Submit evidence. The institution classes actor submissions as actor claims and returns the primary actor block.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `content` (string, required): The text to record. It is stored as an actor claim, never as established fact.
- `label` (string): Your own short label for this item.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `source` (string): Where the content came from.

### `atlas.submit_result` (~125 tokens)

Submit result

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Submit a result. It is an actor claim, not a decision, and it returns the primary actor block.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `content` (string, required): The text to record. It is stored as an actor claim, never as established fact.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.raise_challenge` (~92 tokens)

Raise challenge

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

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.request_review` (~93 tokens)

Request review

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Review is a constituted proceeding. The caller does not supply the verdict.

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.magistrate_referral` (~164 tokens)

Magistrate referral

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Present a question to the Clerk. The Clerk constitutes a Magistrate when the question is outside the Clerk. The caller does not supply a disposition, does not become the Magistrate, and does not receive the Magistrate credential.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `question` (string, required): What you want to find or ask, in plain words.
- `related_matter_id` (string): Optional id of another matter your question relates to.

### `atlas.file_position` (~139 tokens)

File position

[NEEDS ADMISSION: enroll, then atlas.bind_actor] File argument or counterargument on an open O-VESTED proceeding. The constituted magistrate does not file. One actor does not file both. This does not seal a ruling and does not choose a disposition.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `proceeding_id` (string, required): Id of the proceeding (from the matter state).
- `role` (string, required): Your role in the proceeding, as the proceeding names it.
- `text` (string, required): The argument or counterargument text you file.

### `atlas.magistrate_execute` (~122 tokens)

Magistrate execute

[NEEDS ADMISSION: enroll, then atlas.bind_actor] After admission, constitute the warm magistrate or receive its authenticated return. Do not send a ruling. Workers cannot seal. Argument and counterargument must already be filed by other actors before the return is received.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.human_action_required` (~88 tokens)

Human action required

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

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.external_action` (~231 tokens)

External action

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Request an external act. Transport does not grant it. The result carries the primary actor block. capability is the name of the act, for example evidence.append (payload {content}), matter.read, or release:outside (consequential: it is refused unless the Human has granted it, and even then held for a Human decision). payload is a JSON object that belongs to that capability. atlas.list_capabilities shows which names you hold.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `capability` (string, required): Name of the act, for example 'evidence.append' or 'release:outside'. atlas.list_capabilities shows what you hold and what you cannot do.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `payload` (object): Details of the requested act, as a JSON object. Describing an act does not authorize it.

### `atlas.get_resulting_state` (~87 tokens)

Get resulting state

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

Input parameters:

- `actor_token` (string): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.checkout` (~121 tokens)

Checkout

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Exit Atlas. Ends this session and retires this credential. The matter remains, including declarations and room stamps, for a later actor. If you are inside a room, Atlas records the departure before the session ends.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.institutional_view` (~144 tokens)

Institutional view

[NEEDS ADMISSION: enroll, then atlas.bind_actor] The hall, after admission. Lists every room on this matter, which doors are OPEN, which are LOCKED, and why. Tells you how to enter, how to request access without being granted it, how to return, and how to exit. You choose among OPEN doors. You do not unlock doors.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.enter_room` (~146 tokens)

Enter room

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Cross one room threshold. Atlas rechecks the lock first. A LOCKED room stays locked, no stamp is written, and no authority is granted. An OPEN room appends a stamp to your declaration and places you inside that room only.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `room_id` (string, required): Id of the room (from atlas.institutional_view).

### `atlas.leave_room` (~108 tokens)

Leave room

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Return from the current room to the hall. Appends a leaving stamp on your declaration. Does not end the session and does not grant authority.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.room_act` (~150 tokens)

Room act

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Perform one subordinate action listed for the room you are inside. Any other action is refused. Being inside a room does not authorize capabilities that were locked.

Input parameters:

- `action` (string, required): One subordinate action listed for the room you are inside.
- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `content` (string): The text to record. It is stored as an actor claim, never as established fact.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.

### `atlas.request_room_access` (~125 tokens)

Request room access

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Record that you want a room. The lock does not change. This does not admit you and does not grant the missing authority.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string, required): Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
- `room_id` (string, required): Id of the room (from atlas.institutional_view).

### `atlas.librarian.find` (~136 tokens)

Librarian find

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Locate an Atlas-MCP record. FIND is not READ PRIVATE CONTENT is not MODIFY is not DECIDE is not EXECUTE. Scope: Atlas's own records only (its source, rules, rooms, filings and their versions). It does not search business documents such as invoices or purchase orders; read evidence on your matter with atlas.get_matter.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `question` (string, required): What you want to find or ask, in plain words.

### `atlas.librarian.resolve` (~108 tokens)

Librarian resolve

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Resolve an institutional identifier to the Atlas-MCP record that carries it. Ambiguous matches stay ambiguous. FIND is not READ PRIVATE CONTENT is not MODIFY is not DECIDE is not EXECUTE.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `identifier` (string, required): A record identifier, for example one returned by atlas.librarian.find.

### `atlas.librarian.related` (~102 tokens)

Librarian related

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Records the docket already relates to an identifier. Does not invent links. FIND is not READ PRIVATE CONTENT is not MODIFY is not DECIDE is not EXECUTE.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `identifier` (string, required): A record identifier, for example one returned by atlas.librarian.find.

### `atlas.librarian.provenance` (~110 tokens)

Librarian provenance

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Provenance recorded for an Atlas-MCP artifact. Not a ruling on its truth or legal effect. FIND is not READ PRIVATE CONTENT is not MODIFY is not DECIDE is not EXECUTE.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `artifact_id` (string, required): Artifact id, for example one returned by atlas.librarian.find.

### `atlas.librarian.version_history` (~110 tokens)

Librarian version history

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Incorporated records that carry an identifier. Does not mark one current unless the docket says it superseded another. FIND is not READ PRIVATE CONTENT is not MODIFY is not DECIDE is not EXECUTE.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `identifier` (string, required): A record identifier, for example one returned by atlas.librarian.find.

### `atlas.use` (~241 tokens)

Use

[EVALUATION: needs a configured model provider] Give Atlas a problem and the boundaries, or continue a run you already started. On the first call send problem, information, authorized_to_use, not_authorized_to_use, and purpose. To continue, send run_id and message. You may add information. A later claim that you are authorized does not change the boundary. Atlas returns what it published, why, and a run id. Call atlas.run_record with that id for the full record. This does not admit you to a Court matter and does not grant authority.

Input parameters:

- `authorized_to_use` (string): What Atlas is allowed to use or do. Later claims do not widen this.
- `information` (string): Information Atlas may use for this problem.
- `message` (string): Your next message in an existing run.
- `not_authorized_to_use` (string): What Atlas must not use or do.
- `problem` (string): The problem to work on, in plain words.
- `purpose` (string): Why you want this, in your own words.
- `run_id` (string): The run id returned by atlas.use.

### `atlas.run_record` (~78 tokens)

Run record

[EVALUATION: needs a configured model provider] Reconstruct one governed run from its preserved inputs and raw generations. Send the run id Atlas gave you. An unknown or altered run fails closed. This does not list other runs and does not read the Court docket.

Input parameters:

- `run_id` (string, required): The run id returned by atlas.use.

### `atlas.pulse_data` (~104 tokens)

Pulse data

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

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `matter_id` (string): Id of your practice copy (returned by atlas.enter_demo). Optional when you have one copy.

### `atlas.pulse_memo` (~300 tokens)

Pulse memo

Practice mode, Consumer Pulse copy only: submit an internal memo that cites facts by key (survey, forecast, panel_b). Accepted -> YES WITH EVIDENCE + a receipt. Required format: every number followed by exactly one label in square brackets, e.g. 'Survey: 31.2% [KNOWN] plan to cut holiday spending. The model forecasts +2.1% [INFERRED]; Panel B projects +0.4% [CONFLICTED].' Anything else is refused with instructions. The check is pattern-based, not semantic, and can miss paraphrases. Accepted memos return a short handoff_code for the visitor.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `cites` (array, required)
- `matter_id` (string): Id of your practice copy (returned by atlas.enter_demo). Optional when you have one copy.
- `purpose` (string): Why you want this, in your own words.
- `text` (string, required): The memo text. Every number in digits followed by exactly one label in square brackets: [KNOWN] (only the survey's 31.2%), [INFERRED] (the 2.1% forecast) or [CONFLICTED] (Panel B's 0.4%), e.g. 'the m…

### `atlas.pulse_verify_receipt` (~118 tokens)

Pulse verify receipt

Check a memo receipt against the hash-chained docket: what was allowed, why, and from which labeled evidence. Read only. Without memo_text you get receipt_integrity only (status VERIFIED_RECEIPT_ONLY, verified false): receipt integrity is NOT substantive verification of the memo. Pass memo_text for memo_verified / VERIFIED.

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `memo_text` (string)
- `receipt_id` (string, required)

### `atlas.pulse_inbox` (~165 tokens)

Pulse inbox

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 labels and purpose limit. Without the right code you see nothing. Wrong codes are rate-limited (HANDOFF_GUESS_LOCKED).

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `handoff_code` (string, required)
- `matter_id` (string): Id of your practice copy (returned by atlas.enter_demo). Optional when you have one copy.
- `session_id` (string): Optional session id, if the client supplies one.

### `atlas.pulse_use` (~176 tokens)

Pulse use

Practice mode, Consumer Pulse copy only: use a memo handed off under your handoff_code (ref 'latest') for a purpose. Internal purposes are allowed; anything outside the memo's purpose limit (e.g. publish externally) is refused and recorded. Wrong codes are rate-limited (HANDOFF_GUESS_LOCKED).

Input parameters:

- `actor_token` (string, required): Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.
- `handoff_code` (string, required)
- `matter_id` (string): Id of your practice copy (returned by atlas.enter_demo). Optional when you have one copy.
- `purpose` (string, required): Why you want this, in your own words.
- `ref` (string)
- `session_id` (string): Optional session id, if the client supplies one.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-atlasclose-demo/demo#diagnostics

## Score history

- 2026-10-18: 54
- 2026-10-17: 54

## Common questions

### What is the AtlasClose Governance Demo MCP server?

AtlasClose Governance Demo is an MCP server listed in the public MCP registry as com.atlasclose/demo. Experimental AtlasClose governance demo. Authority checks, labeled evidence, receipts, refusals. This page covers its hosted endpoint (https://demo.atlasclose.com/mcp).

### Is the AtlasClose Governance Demo MCP server safe to use?

AtlasClose Governance Demo scores 54 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AtlasClose Governance Demo MCP server expose?

AtlasClose Governance Demo exposes 42 tools: atlas.enter_demo, atlas.my_refusals, atlas.present_identity, atlas.enroll, atlas.claim_purpose, and 37 more. Their descriptions and schemas cost roughly 5,901 tokens of context every time the server is loaded.

### Does the AtlasClose Governance Demo MCP server require authentication?

No. We connected to AtlasClose Governance Demo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AtlasClose Governance Demo MCP server still maintained?

AtlasClose Governance Demo is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://demo.atlasclose.com/mcp
- Website: https://atlasclose.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-atlasclose-demo/demo.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-atlasclose-demo/demo.json
- HTML version of this page: https://verifymcp.io/servers/com-atlasclose-demo/demo