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.
- 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.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "set": a word for a change.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_task" says "start": a word for a change.
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
refine_legal_queryRestates one Australian legal question and lists the clarifying questions still open: state or territory, dates, parties, forum, output and urgency.No findings
Why it is in this group
- The name "refine_legal_query" says "query": a word for reading.
Description, as the server wrote it Restates one Australian legal question and lists the clarifying questions still open: state or territory, dates, parties, forum, output and urgency.
Annotations the server declares
- title: Refine a legal question
- 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.
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.
What this check looks forMatched 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)
Findings
Matches of fixed checks, with the text they matched.
- Warnstart_task
The server marks "start_task" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_task" says "start": a word for a change.
- Warnrecord_answers
The server marks "record_answers" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.
- Warnrecord_research
The server marks "record_research" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "add": a word for a change.
- Warnplan_human_work
The server marks "plan_human_work" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "set": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 changed.~5 changedView diff
- Changed:assess_tool_useOnly readsdescription
- Changed:disclosure_dutiesOnly readsdescriptioninputSchema
- Changed:find_rulesOnly readsdescriptioninputSchema
- Changed:get_jurisdiction_guidanceOnly readsdescriptioninputSchema
- Changed:search_libraryOnly readsdescriptioninputSchema
Tools5 added.+5 addedView diff
- Added:assess_tool_useOnly reads
- Added:disclosure_dutiesOnly reads
- Added:find_rulesOnly reads
- Added:get_practice_area_promptOnly reads
- Added:refine_legal_queryOnly reads
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/mcpclaude mcp add --transport http ai-law-framework https://ailawframework.com/mcpRun 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.
{
"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.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](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.