Skip to content

AI Law Framework MCP server

com.ailawframework/ai-law-frameworkailawframework.comstreamable-httpv1.1.0Scanned

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

19 tools: 5 change things and 14 only read.

Tools: 0 delete, 0 irreversible, 5 write, 14 read.
  • Reads private data · 2
  • Reads text others write · 2
  • Can send data out · 0
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AI Law Framework MCP server can do

The AI Law Framework MCP server is published by ailawframework.com, a domain the MCP Registry verified. It has 19 tools. It can create or change data (5 tools: start_task, record_answers, record_research, assess_and_decide and 1 more), but cannot delete data. 14 tools only read.

2 tools read private data (get_jurisdiction_guidance and disclosure_duties); 2 tools bring in text other people can write (get_task_guidance and get_software_profile).

The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 1.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

19 tools

Changes things 5Claude Code: ask
  • assess_and_decideScores 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 t…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Assess and decide
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • plan_human_workSets 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 …1 finding

    Why it is in this group

    • The description's first verb is "set": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "plan_human_work" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "set": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Plan the human work
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • record_answersAdds the user’s answers to the clarifying questions to the work record.1 finding

    Why it is in this group

    • The description's first verb is "add": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "record_answers" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Record the user’s answers
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • record_researchAdds research findings, each with its source, quote and confirmation status, to the work record.1 finding

    Why it is in this group

    • The description's first verb is "add": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "record_research" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Record research findings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • start_taskOpens 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`.1 finding

    Why it is in this group

    • The name "start_task" says "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "start_task" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_task" says "start": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Start a task under the framework
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 14Show 14 read-only tools
  • assess_tool_useReturns the catalogue adoption, efficiency and governance for one tool on one task, plus the matching court AI rules.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Returns the catalogue adoption, efficiency and governance for one tool on one task, plus the matching court AI rules. Unlisted tools stay not_recorded.

    Annotations the server declares

    • title: Assess an AI tool for a task
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • disclosure_dutiesReturns the stored disclosure and verification duties for a forum and a document type.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "document": it reads documents.
    Description, as the server wrote it
    Returns the stored disclosure and verification duties for a forum and a document type. United States: the recorded court and client answers for the state, DC or federal courts as stored, and the stored rules and orders whose summaries say filers must disclose or certify.

    Annotations the server declares

    • title: Disclosure duties for a document
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • find_rulesReturns the stored court and tribunal AI instruments that match a task and a forum, using the catalogue rule matcher.No findings

    Why it is in this group

    • The name "find_rules" says "find": a word for reading.
    Description, as the server wrote it
    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. Court decisions about AI use are listed apart in `related_decisions`; they are not rules. United States: a state or DC (US-TX), or US-FED with federal_court and judge, returns that forum’s stored records grouped, each with whom it binds and its page.

    Annotations the server declares

    • title: Find court AI rules
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_frameworkReturns 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…No findings

    Why it is in this group

    • The name "get_framework" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Read the framework
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_jurisdiction_guidanceReturns the framework’s notes for one jurisdiction, and which stored AI instruments apply to a task in a court or tribunal.Reads private dataNo findings

    Why it is in this group

    • The name "get_jurisdiction_guidance" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "note": it reads notes.
    Description, as the server wrote it
    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. It also returns the jurisdiction’s recorded answers on telling the court and the client, with their basis and sources, and the instruments its page lists with their dates (up to 30, instruments before notes; ai_rules_more counts the rest). A row of kind no_guidance_note records that none was found. Each instrument’s summary is on the page at md_url.

    Annotations the server declares

    • title: Get a jurisdiction’s guidance
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_practice_area_promptReturns the published practice-area prompt for one Australian area.No findings

    Why it is in this group

    • The name "get_practice_area_prompt" says "get": a word for reading.
    Description, as the server wrote it
    Returns the published practice-area prompt for one Australian area. Court AI rules are attached when a jurisdiction code is given.

    Annotations the server declares

    • title: Get a practice-area prompt
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_precedentReturns 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…No findings

    Why it is in this group

    • The name "get_precedent" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get a precedent’s details
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_software_profileReturns the framework’s research on one AI product and plan: its facts, the governance considerations found, and the cited sources with their review dates.Reads text others writeNo findings

    Why it is in this group

    • The name "get_software_profile" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "return" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get a software profile
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_startedFor 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 starti…No findings

    Why it is in this group

    • The name "get_started" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get started with the framework
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_task_guidanceReturns 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.Reads text others writeNo findings

    Why it is in this group

    • The name "get_task_guidance" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "return" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get a task’s guidance
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_librarySearches the framework’s published practice areas, tasks, jurisdiction versions, jurisdictions, firm-wide obligations, software profiles, precedents and workflows.No findings

    Why it is in this group

    • The name "search_library" says "search": a word for reading.
    Description, as the server wrote it
    Searches the framework’s published practice areas, tasks, jurisdiction versions, jurisdictions, firm-wide obligations, software profiles, precedents and workflows. Returns titles, ids, ailawframework.com links and their markdown versions.

    Annotations the server declares

    • title: Search the practice library
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_precedentsSearches the published precedent library (letters, agreements, clauses, checklists, forms, policies and more for every practice area) by title, summary and when to use it.No findings

    Why it is in this group

    • The name "search_precedents" says "search": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Search the precedent library
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • work_recordReturns 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.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Produce the work record
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:33 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ailawframework.com/mcp: tools/list returned 19 tools to an anonymous client, including start_task (write), record_answers (write), record_research (write), assess_and_decide (write), plan_human_work (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 warn
  • The server marks "start_task" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_task" says "start": a word for a change.

    What this check looks for
  • The server marks "record_answers" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.

    What this check looks for
  • The server marks "record_research" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.

    What this check looks for
  • The server marks "plan_human_work" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "set": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools5 changed.~5 changedView diff
  2. Tools5 added.+5 addedView diff

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ai-law-framework https://ailawframework.com/mcp
claude mcp add --transport http ai-law-framework https://ailawframework.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ai-law-framework__work_record",
      "mcp__ai-law-framework__search_library",
      "mcp__ai-law-framework__get_task_guidance",
      "mcp__ai-law-framework__get_jurisdiction_guidance",
      "mcp__ai-law-framework__get_software_profile",
      "mcp__ai-law-framework__search_precedents",
      "mcp__ai-law-framework__get_precedent",
      "mcp__ai-law-framework__get_started",
      "mcp__ai-law-framework__get_framework",
      "mcp__ai-law-framework__refine_legal_query",
      "mcp__ai-law-framework__get_practice_area_prompt",
      "mcp__ai-law-framework__find_rules",
      "mcp__ai-law-framework__assess_tool_use",
      "mcp__ai-law-framework__disclosure_duties"
    ],
    "ask": [
      "mcp__ai-law-framework__start_task",
      "mcp__ai-law-framework__record_answers",
      "mcp__ai-law-framework__record_research",
      "mcp__ai-law-framework__assess_and_decide",
      "mcp__ai-law-framework__plan_human_work"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-law-framework. Review it before you use it.

Capability tags behind 4 rules
  • mcp__ai-law-framework__get_task_guidance untrusted-input
  • mcp__ai-law-framework__get_jurisdiction_guidance private-data
  • mcp__ai-law-framework__get_software_profile untrusted-input
  • mcp__ai-law-framework__disclosure_duties private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.ailawframework/ai-law-framework/verify?hash=effe603d8df2dcefe80c1be83d3df75d961e04a81a65c696568ca0d4ae1ab78e" | jq -e '.changed == false'

Pinned hash effe603d8df2, from Nov 12, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.ailawframework/ai-law-framework/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.ailawframework/ai-law-framework
[![Anlyon Radar](https://radar.anlyon.com/badge/com.ailawframework/ai-law-framework.svg)](https://radar.anlyon.com/servers/com.ailawframework/ai-law-framework)

Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.

AI Law Framework MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AI Law Framework MCP server safe?

No scan can promise that. What its definitions show: 19 tools, 5 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AI Law Framework MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AI Law Framework MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AI Law Framework MCP server have?

19 tools: 5 write, 14 read. start_task, record_answers, record_research, assess_and_decide, plan_human_work, work_record, search_library, get_task_guidance and 11 more.

Does the AI Law Framework MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AI Law Framework MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AI Law Framework MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.