# AI Obligations Atlas (remote · obligations-atlas.triodian.com)

AI governance obligations in Australia and Singapore, by source tier and use case. No key needed.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `obligations-atlas.triodian.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas.md), [page](https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas)

## Channel facts

- Endpoint: `https://obligations-atlas.triodian.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1565 tokens (~391/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 57% of tool parameters carry a description.
- **Tool Safety**: 50/100
  - Injection-marker check failed: the server instructions contains an instruction to conceal the call from the user, the text "never tell the user", at byte 749 of that field, plus 3 further marker(s) of the same kind.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the AI Obligations Atlas MCP server?

AI Obligations Atlas is a hosted endpoint at https://obligations-atlas.triodian.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 triodian-obligations-atlas 'https://obligations-atlas.triodian.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "triodian-obligations-atlas": {
      "url": "https://obligations-atlas.triodian.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "triodian-obligations-atlas": {
      "type": "http",
      "url": "https://obligations-atlas.triodian.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.triodian-obligations-atlas]
url = "https://obligations-atlas.triodian.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add triodian-obligations-atlas --url 'https://obligations-atlas.triodian.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  triodian-obligations-atlas:
    url: "https://obligations-atlas.triodian.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "triodian-obligations-atlas": {
      "Transport": "http",
      "Url": "https://obligations-atlas.triodian.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add triodian-obligations-atlas -t streamable-http -u 'https://obligations-atlas.triodian.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "triodian-obligations-atlas": {
      "type": "http",
      "url": "https://obligations-atlas.triodian.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.

### 2026-11-19 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_obligations” rewrote its description, which is the text the model reads
- [security] Tool “get_obligation” rewrote its description, which is the text the model reads
- [security] Tool “list_changes” rewrote its description, which is the text the model reads
- [cosmetic] “find_obligations” reworded the description of “jurisdiction”

### 2026-11-14 (score 65, 0)

- [cosmetic] “find_obligations” reworded the description of “jurisdiction”

### 2026-11-13 (score 65, +1)

- [cosmetic] “find_obligations” reworded the description of “tier”

### 2026-11-11 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 63, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-08 (score 62)

First indexed and scored.

## MCP tools (4)

### `find_obligations` (~665 tokens)

Find AI governance obligations

Search the AI Obligations Atlas for AI governance obligations by jurisdiction, source tier, standardised AI use case (UC1-UC10), entity type or text. Returns sourced records with tier, status, key dates, source link and provenance reference. Coverage: the Atlas holds records for Australia, Singapore, the United States (federal and state) and international standards. When a response carries a coverage note for a jurisdiction, tell the user that the Atlas does not yet cover it; never read an empty result as meaning no obligations apply. Records with appliesToAnyAIUse apply to any AI use rather than to particular use cases. Responses are records, not legal conclusions. When you quote a record, cite its source link, tier and last-verified date (the citeAs field does this). Describe tiers as describing sources: never tell the user that they or a client are compliant, in breach, or required to do something; say what the source says and that counsel decides what applies. For Anticipated records give the status or key date, never a likelihood that the source will pass or apply. Records state what sources say and how they are classified. They are not legal advice and do not say what the law requires of any particular client; counsel decides what applies.

Input parameters:

- `current` (boolean): Exclude superseded, repealed and withdrawn records
- `entityType` (array): Entity types, e.g. authorisedDepositTakingInstitution, generalInsurer, superannuationTrustee, bank, insurer, listedEntity, or for organisations outside financial regulation privateCompany, notForProf…
- `includeAnyUse` (boolean): false to leave out records that apply to any AI use when filtering by use case
- `includeInternational` (boolean)
- `jurisdiction` (array): Jurisdiction codes. A US state is its ISO 3166-2 code, such as US-NY: asking for US lists federal and every state's records; asking for US-NY lists New York's and the federal ones. Covered now: AU, S…
- `limit` (integer)
- `q` (string): Text to match in title, statement, instrument or citation
- `sector` (array): Regulated sectors, e.g. AU-BANKING, AU-INSURANCE, AU-SUPERANNUATION, AU-GENERAL, SG-BANKING (see the dataset's sectors). A sector sets its jurisdiction and its entity types.
- `tier` (array): Source tiers. adopted: a voluntary standard a client has adopted for itself, such as ISO/IEC 42001:2023 Annex A
- `useCase` (array): Standardised use cases, e.g. UC3 (automated triage or decline), UC7 (AI inside a provider). Records specific to these come first, then records that apply to any AI use.

### `get_obligation` (~263 tokens)

Get one obligation

Get one Atlas obligation record by its ID (e.g. OBL-AU-CPS230-47), with tier basis, key dates, source link, last-verified date and provenance reference. Coverage: the Atlas holds records for Australia, Singapore, the United States (federal and state) and international standards. When a response carries a coverage note for a jurisdiction, tell the user that the Atlas does not yet cover it; never read an empty result as meaning no obligations apply. Records with appliesToAnyAIUse apply to any AI use rather than to particular use cases. Responses are records, not legal conclusions. When you quote a record, cite its source link, tier and last-verified date (the citeAs field does this). Describe tiers as describing sources: never tell the user that they or a client are compliant, in breach, or required to do something; say what the source says and that counsel decides what applies. For Anticipated records give the status or key date, never a likelihood that the source will pass or apply. Records state what sources say and how they are classified. They are not legal advice and do not say what the law requires of any particular client; counsel decides what applies.

Input parameters:

- `obligationID` (string, required)

### `list_changes` (~267 tokens)

List changes since a date

List new and amended instruments, commencements, withdrawals and record updates in the Atlas since a date (YYYY-MM-DD), newest first. Leads from commentary are marked as leads, not verified changes. Coverage: the Atlas holds records for Australia, Singapore, the United States (federal and state) and international standards. When a response carries a coverage note for a jurisdiction, tell the user that the Atlas does not yet cover it; never read an empty result as meaning no obligations apply. Records with appliesToAnyAIUse apply to any AI use rather than to particular use cases. Responses are records, not legal conclusions. When you quote a record, cite its source link, tier and last-verified date (the citeAs field does this). Describe tiers as describing sources: never tell the user that they or a client are compliant, in breach, or required to do something; say what the source says and that counsel decides what applies. For Anticipated records give the status or key date, never a likelihood that the source will pass or apply. Records state what sources say and how they are classified. They are not legal advice and do not say what the law requires of any particular client; counsel decides what applies.

Input parameters:

- `jurisdiction` (string)
- `since` (string, required)

### `explain_provenance` (~78 tokens)

Explain a record’s provenance

Explain where an Atlas record came from: the sources read, validation, matching, conflicts resolved, confidence, treatment under the published autonomy rules, and the named approver. Accepts an obligation ID, governed record ID (ID@version) or provenance record ID. Each ledger entry is hash-checked.

Input parameters:

- `ref` (string, required)

## Diagnostics

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

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 68
- 2026-11-18: 67
- 2026-11-17: 67
- 2026-11-16: 66
- 2026-11-15: 66
- 2026-11-14: 65
- 2026-11-13: 65
- 2026-11-12: 64
- 2026-11-11: 64
- 2026-11-10: 63
- 2026-11-09: 63
- 2026-11-08: 62

## Common questions

### What is the AI Obligations Atlas MCP server?

AI Obligations Atlas is an MCP server listed in the public MCP registry as io.github.Triodian/obligations-atlas. AI governance obligations in Australia and Singapore, by source tier and use case. No key needed. This page covers its hosted endpoint (https://obligations-atlas.triodian.com/mcp).

### Is the AI Obligations Atlas MCP server safe to use?

AI Obligations Atlas scores 68 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 AI Obligations Atlas MCP server expose?

AI Obligations Atlas exposes 4 tools: find_obligations, get_obligation, list_changes, explain_provenance. Their descriptions and schemas cost roughly 1,273 tokens of context every time the server is loaded.

### Does the AI Obligations Atlas MCP server require authentication?

No. We connected to AI Obligations Atlas without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AI Obligations Atlas MCP server still maintained?

AI Obligations Atlas is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AI Obligations Atlas MCP server?

VerifyMCP ran 13 checks on AI Obligations Atlas, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://obligations-atlas.triodian.com/mcp
- Repository: https://github.com/Triodian/obligations-atlas
- Website: https://obligations-atlas.triodian.com/
- Changelog RSS feed: https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas.xml
- Changelog JSON feed: https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas.json
- HTML version of this page: https://verifymcp.io/servers/triodian-obligations-atlas/obligations-atlas
