# AI Law Framework (remote · ailawframework.com)

Decide whether AI may be used for a legal task, who drafts and who checks. Australian law.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `ailawframework.com`: 83/100 (this document), [markdown](https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework.md), [page](https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework)

## Channel facts

- Endpoint: `https://ailawframework.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-05.

- **Endpoint Security**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3489 tokens (~99/item across 35 items; 19 tools + 16 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AI Law Framework MCP server?

AI Law Framework is a hosted endpoint at https://ailawframework.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-ailawframework-ai-law-framework 'https://ailawframework.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-ailawframework-ai-law-framework": {
      "url": "https://ailawframework.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ailawframework-ai-law-framework": {
      "type": "http",
      "url": "https://ailawframework.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-ailawframework-ai-law-framework]
url = "https://ailawframework.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-ailawframework-ai-law-framework --url 'https://ailawframework.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-ailawframework-ai-law-framework:
    url: "https://ailawframework.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-ailawframework-ai-law-framework": {
      "Transport": "http",
      "Url": "https://ailawframework.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ailawframework-ai-law-framework -t streamable-http -u 'https://ailawframework.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-ailawframework-ai-law-framework": {
      "type": "http",
      "url": "https://ailawframework.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.

### 2026-11-04 (score 83, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “assess_tool_use” rewrote its description, which is the text the model reads

### 2026-11-02 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 81, 0)

- [security] Tool “find_rules” rewrote its description, which is the text the model reads

### 2026-10-31 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 78, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 2672 → 3457
- [functional] MCP protocol: Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
- [functional] New prompt “practice-area-class-actions”
- [functional] New prompt “practice-area-commercial”
- [functional] New prompt “practice-area-criminal”
- [functional] New prompt “practice-area-employment”
- [functional] New prompt “practice-area-family”
- [functional] New prompt “practice-area-personal-injury”
- [functional] New prompt “practice-area-property”
- [functional] New prompt “practice-area-wills-estates”
- [functional] MCP protocol version: 2026-07-28 → 2025-11-25
- [functional] New resource “legal-assistant”
- [functional] New tool “assess_tool_use”
- [functional] New tool “disclosure_duties”
- [functional] New tool “find_rules”
- [functional] New tool “get_practice_area_prompt”
- [functional] New tool “refine_legal_query”

### 2026-10-25 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (19)

### `start_task` (~165 tokens)

Start a task under the framework

Opens a work record for one legal task and returns the clarifying questions the framework needs answered (step 1, define the task), less any already answered in `answers`. The first two are the country and, in Australia, the state or territory: ask them first. Read the skill ailf://skills/ai-law-framework before the first call.

Input parameters:

- `agent` (string): The agent and product doing the work, for example "Claude Code" or "Codex".
- `answers` (object): Answers keyed by question id. `from` is "user" when the user answered when asked, or "request" when the user had already said it (then `quote` holds their words).
- `request` (string, required): The user’s request, in their words.

### `record_answers` (~109 tokens)

Record the user’s answers

Adds the user’s answers to the clarifying questions to the work record. Returns the questions still open, or, once all are answered, the research the task requires.

Input parameters:

- `answers` (object, required): Answers keyed by question id. `from` is "user" when the user answered when asked, or "request" when the user had already said it (then `quote` holds their words).
- `record` (string, required): The `record` string the previous workflow tool returned, passed back unchanged.

### `record_research` (~75 tokens)

Record research findings

Adds research findings, each with its source, quote and confirmation status, to the work record. Returns the required research still missing, or the scoring anchors and the governance ceiling the evidence sets.

Input parameters:

- `findings` (array, required)
- `record` (string, required): The `record` string the previous workflow tool returned, passed back unchanged.

### `assess_and_decide` (~206 tokens)

Assess and decide

Scores the AI option on adoption, efficiency and governance (step 2), caps governance by the recorded evidence, scores the manual route, and returns the decision, its reasons and the order of preference.

Input parameters:

- `adoption` (object, required): Adoption feasibility: the anchor that is true for this option on this task.
- `conditions` (object): A recorded condition that removes the cause of a 2 on adoption or efficiency.
- `efficiency` (object, required): Efficiency likelihood: the anchor that is true for this option on this task.
- `efficiency_confidence` (string)
- `governance` (object, required): Governance suitability: the anchor that is true for this option on this task.
- `option_name` (string, required): The AI option as configured, for example "Claude Code on a Team plan".
- `outstanding` (boolean): True when a document, setting or check is still outstanding.
- `record` (string, required): The `record` string the previous workflow tool returned, passed back unchanged.

### `plan_human_work` (~74 tokens)

Plan the human work

Sets the level of each of the seven stages of the task (step 3) from the recorded answers, research and decision, and returns what the lawyer and the AI may and may not do at each stage.

Input parameters:

- `record` (string, required): The `record` string the previous workflow tool returned, passed back unchanged.

### `work_record` (~149 tokens)

Produce the work record

Returns the work record as markdown (steps 4 and 5): the task, the evidence, the decision, the plan, what the AI did, and the checks, approval and release left for the lawyer.

Input parameters:

- `agent_did` (array): What the AI did, one line per stage worked on.
- `check_points` (array): Each high-risk point to check against its document: dates, figures, key advice.
- `lawyer_checkpoints` (array): The task’s review points from get_task_guidance.
- `notes` (string)
- `output` (object, required)
- `record` (string, required): The `record` string the previous workflow tool returned, passed back unchanged.

### `search_library` (~72 tokens)

Search the practice library

Searches the framework’s published practice areas, tasks, jurisdiction versions, jurisdictions, firm-wide obligations and software profiles. Returns titles, ids and ailawframework.com links.

Input parameters:

- `kind` (string)
- `limit` (integer)
- `query` (string, required): Words describing the task, area, jurisdiction or product.

### `get_task_guidance` (~94 tokens)

Get a task’s guidance

Returns one task from the practice library: how AI may be used, its level, what the lawyer must review, its checkpoints, restrictions and sources, and its jurisdiction versions.

Input parameters:

- `jurisdiction` (string): Optional jurisdiction id or slug, for example "NSW", to include that version.
- `task_id` (string, required): The task id from search_library, for example "A1-A20260923-1".

### `get_jurisdiction_guidance` (~216 tokens)

Get a jurisdiction’s guidance

Returns the framework’s notes for one jurisdiction, and which stored AI instruments apply to a task in a court or tribunal. Name the forum, or court "no" when no court is involved. A gap means no instrument is stored for that forum.

Input parameters:

- `audience` (string)
- `court` (string): no when no court or tribunal is involved.
- `document_type` (string): affidavit, witness-statement, expert-report, submissions, pleadings, contract or chronology.
- `forum` (string): A forum code such as "ncat", "federal-court" or "vcat". Omit it to be asked which court applies.
- `jurisdiction` (string, required): A jurisdiction id or slug, for example "NSW", "VIC", "new-zealand".
- `personal_information` (boolean): True when the work puts personal information into an AI product.
- `task` (string): What the work is, in a short phrase. Used to recognise the document and the subject.

### `get_software_profile` (~100 tokens)

Get a software profile

Returns the framework’s research on one AI product and plan: its facts, the governance considerations found, and the cited sources with their review dates. Accepts a profile id or a product name.

Input parameters:

- `controls` (array): Optional control ids, such as "trainingUse" or "inferenceRegion", to return only those considerations.
- `product` (string, required): A profile id from search_library, or a product name such as "Claude Team".

### `search_precedents` (~121 tokens)

Search the precedent library

Searches the published precedent library (letters, agreements, clauses, checklists, forms, policies and more for every practice area) by title, summary and when to use it. Returns ids, titles, kinds, practice area ids, jurisdictions and the date each states the law as at. The full text is available through the signed-in firm connector.

Input parameters:

- `area` (string): Optional practice area id, for example "A1".
- `limit` (integer)
- `query` (string, required): Words to search for, 2 to 200 characters.

### `get_precedent` (~91 tokens)

Get a precedent’s details

Returns one published precedent’s details: summary, when to use it, authorities, the AI-use guidance (level, what AI may and must not do, what the lawyer checks), licence, the date it states the law as at and how the library maintains it. The text itself is available through the signed-in firm connector.

Input parameters:

- `precedent_id` (string, required): The precedent id from search_precedents.

### `get_started` (~66 tokens)

Get started with the framework

For a new user, or when asked what this is: what the AI Law Framework decides, the first questions it asks (country, then state or territory), the five steps, the skills and starting prompts, and a fictional sample matter the user can run to see a finished work record.

### `get_framework` (~57 tokens)

Read the framework

Returns the AI Law Framework’s rules: the five steps, the three pillars and their anchors, the decision rule, the four levels, the seven stages and their matrix, and the rules that admit no exception.

Input parameters:

- `part` (string)

### `refine_legal_query` (~79 tokens)

Refine a legal question

Restates one Australian legal question and lists the clarifying questions still open: state or territory, dates, parties, forum, output and urgency.

Input parameters:

- `area` (string): Optional practice-area id. Omitted means the question is classified from its words.
- `query` (string, required): The legal question, with client names and contact details removed.

### `get_practice_area_prompt` (~107 tokens)

Get a practice-area prompt

Returns the published practice-area prompt for one Australian area. Court AI rules are attached when a jurisdiction code is given.

Input parameters:

- `area` (string, required)
- `jurisdiction` (string): Optional code: NSW, VIC, QLD, WA, SA, TAS, ACT, NT or CTH (use CTH for federal forums such as the Federal Court, FCFCOA and the Fair Work Commission). Omit it to be asked. No code is filled in for yo…

### `find_rules` (~174 tokens)

Find court AI rules

Returns the stored court and tribunal AI instruments that match a task and a forum, using the catalogue rule matcher. With a forum named, guidance for the jurisdiction that is not tagged to that forum is returned apart, in `profession_guidance`; read it too.

Input parameters:

- `forum` (string): A forum code such as ncat or federal-court. Omit it to be asked which court applies.
- `jurisdiction` (string): Optional code: NSW, VIC, QLD, WA, SA, TAS, ACT, NT or CTH (use CTH for federal forums such as the Federal Court, FCFCOA and the Fair Work Commission). Omit it to be asked. No code is filled in for yo…
- `task` (string, required): The legal task, in a short phrase, with client names removed.

### `assess_tool_use` (~150 tokens)

Assess an AI tool for a task

Returns the catalogue adoption, efficiency and governance for one tool on one task, plus the matching court AI rules. Unlisted tools stay not_recorded.

Input parameters:

- `forum` (string): Optional forum code.
- `jurisdiction` (string): Optional code: NSW, VIC, QLD, WA, SA, TAS, ACT, NT or CTH (use CTH for federal forums such as the Federal Court, FCFCOA and the Fair Work Commission). Omit it to be asked. No code is filled in for yo…
- `task` (string, required): The legal task, in a short phrase, with client names removed.
- `tool` (string, required): The AI product name or catalogue profile id.

### `disclosure_duties` (~134 tokens)

Disclosure duties for a document

Returns the stored disclosure and verification duties for a forum and a document type.

Input parameters:

- `document` (string, required): The document the duty is for, such as an affidavit or submissions.
- `forum` (string, required): A forum code such as nsw-supreme-court or federal-court.
- `jurisdiction` (string): Optional code: NSW, VIC, QLD, WA, SA, TAS, ACT, NT or CTH (use CTH for federal forums such as the Federal Court, FCFCOA and the Fair Work Commission). Omit it to be asked. No code is filled in for yo…

## Diagnostics

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

## Score history

- 2026-11-05: 83
- 2026-11-04: 83
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 81
- 2026-10-31: 81
- 2026-10-30: 80
- 2026-10-29: 80
- 2026-10-28: 79
- 2026-10-27: 79
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 77
- 2026-10-23: 77
- 2026-10-22: 76
- 2026-10-21: 76
- 2026-10-20: 75
- 2026-10-19: 75
- 2026-10-18: 74
- 2026-10-17: 74

## Common questions

### What is the AI Law Framework MCP server?

AI Law Framework is an MCP server listed in the public MCP registry as com.ailawframework/ai-law-framework. Decide whether AI may be used for a legal task, who drafts and who checks. Australian law. This page covers its hosted endpoint (https://ailawframework.com/mcp).

### Is the AI Law Framework MCP server safe to use?

AI Law Framework scores 83 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 Law Framework MCP server expose?

AI Law Framework exposes 19 tools: start_task, record_answers, record_research, assess_and_decide, plan_human_work, and 14 more. Their descriptions and schemas cost roughly 2,239 tokens of context every time the server is loaded.

### Does the AI Law Framework MCP server require authentication?

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

### Is the AI Law Framework MCP server still maintained?

AI Law Framework is still listed as active in the MCP registry. We last reached this channel on 5 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 Law Framework MCP server?

VerifyMCP ran 13 checks on AI Law Framework, 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://ailawframework.com/mcp
- Website: https://ailawframework.com/connect
- Changelog RSS feed: https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework.json
- HTML version of this page: https://verifymcp.io/servers/com-ailawframework-ai-law-framework/ailawframework