com.ailawframework/ai-law-framework

Est-ce que com.ailawframework/ai-law-framework est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.ailawframework/ai-law-framework » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 14 outils

• assess_and_decide≈ 592 tokens

  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.

  Paramètres, retour & exemple (8)

  Paramètres

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

  Exemple d'appel

  {"name": "assess_and_decide", "arguments": {"record": "texte", "adoption": {}, "efficiency": {}, "governance": {}, "option_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_framework≈ 144 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • part · string · optionnel · all | steps | pillars | decision | levels | stages | rules

  Exemple d'appel

  {"name": "get_framework", "arguments": {"part": "all"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_jurisdiction_guidance≈ 364 tokens

  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.

  Paramètres, retour & exemple (7)

  Paramètres

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

  Exemple d'appel

  {"name": "get_jurisdiction_guidance", "arguments": {"jurisdiction": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_precedent≈ 178 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • precedent_id · string · requis
    The precedent id from search_precedents.

  Exemple d'appel

  {"name": "get_precedent", "arguments": {"precedent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_software_profile≈ 208 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • product · string · requis
    A profile id from search_library, or a product name such as "Claude Team".
  • controls · array · optionnel
    Optional control ids, such as "trainingUse" or "inferenceRegion", to return only those considerations.

  Exemple d'appel

  {"name": "get_software_profile", "arguments": {"product": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_started≈ 141 tokens

  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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_started", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_task_guidance≈ 182 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • task_id · string · requis
    The task id from search_library, for example "A1-A20260923-1".
  • jurisdiction · string · optionnel
    Optional jurisdiction id or slug, for example "NSW", to include that version.

  Exemple d'appel

  {"name": "get_task_guidance", "arguments": {"task_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• plan_human_work≈ 153 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • record · string · requis
    The `record` string the previous workflow tool returned, passed back unchanged.

  Exemple d'appel

  {"name": "plan_human_work", "arguments": {"record": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_answers≈ 2108 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • record · string · requis
    The `record` string the previous workflow tool returned, passed back unchanged.
  • answers · object · requis
    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).

  Exemple d'appel

  {"name": "record_answers", "arguments": {"record": "texte", "answers": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_research≈ 430 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • record · string · requis
    The `record` string the previous workflow tool returned, passed back unchanged.
  • findings · array · requis

  Exemple d'appel

  {"name": "record_research", "arguments": {"record": "texte", "findings": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_library≈ 197 tokens

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

  Paramètres, retour & exemple (3)

  Paramètres

  • kind · string · optionnel · task | task-version | practice-area | obligation | jurisdiction | software
  • limit · integer · optionnel
  • query · string · requis
    Words describing the task, area, jurisdiction or product.

  Exemple d'appel

  {"name": "search_library", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_precedents≈ 224 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • area · string · optionnel
    Optional practice area id, for example "A1".
  • limit · integer · optionnel
  • query · string · requis
    Words to search for, 2 to 200 characters.

  Exemple d'appel

  {"name": "search_precedents", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• start_task≈ 2170 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent · string · optionnel
    The agent and product doing the work, for example "Claude Code" or "Codex".
  • answers · object · optionnel
    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 · requis
    The user’s request, in their words.

  Exemple d'appel

  {"name": "start_task", "arguments": {"request": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• work_record≈ 336 tokens

  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.

  Paramètres, retour & exemple (6)

  Paramètres

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

  Exemple d'appel

  {"name": "work_record", "arguments": {"output": {}, "record": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://ailawframework.com/mcp