io.github.phwizard/mcp-agrus-ai

Est-ce que io.github.phwizard/mcp-agrus-ai est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.phwizard/mcp-agrus-ai » 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 7 outils

• get_case_study≈ 208 tokens

  Returns one or more Agrus case studies (NDA-protected; customer names are kept private, codenames + technology + outcomes are open). Filter by slug or vertical, or call with no args to list all. Use this for proof of prior work.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · optionnel
    Specific case-study slug. If omitted, returns all available case studies (filtered by vertical if provided).
  • vertical · string · optionnel · healthcare | insurance | legal | private_equity | family_offices | corporate_intelligence | sports | other
    Filter case studies by vertical. Ignored if slug is provided.

  Exemple d'appel

  {"name": "get_case_study", "arguments": {"slug": "texte", "vertical": "healthcare"}}

  Exemple de retour

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

• list_services≈ 177 tokens

  Lists Agrus's six service pillars with descriptions, deliverables, and price bands. Plus the four published pricing tiers (Scoping Call, Discovery Sprint, Build Engagement, Managed SLA). Use this for the 'what does Agrus do?' question.

  Paramètres, retour & exemple (1)

  Paramètres

  • vertical · string · optionnel · healthcare | insurance | legal | private_equity | family_offices | corporate_intelligence | sports | other
    Filter services by vertical applicability. Currently all services apply to all verticals.

  Exemple d'appel

  {"name": "list_services", "arguments": {"vertical": "healthcare"}}

  Exemple de retour

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

• list_verticals≈ 111 tokens

  Lists Agrus's seven year-one verticals (healthcare, insurance, legal, private equity, family offices, corporate intelligence, pro sports) with compliance pins, sample use cases, and the sequencing rationale. Use this for the 'do they work in my industry?' question.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_verticals", "arguments": {}}

  Exemple de retour

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

• query_compliance_position≈ 312 tokens

  Returns Agrus's documented position on a specific regulatory regime (HIPAA, SOC 2, ISO 27001, EU AI Act, NAIC, ABA Model Rules, AML/KYC) as it applies to a described AI use case. Includes key controls, common gotchas, the first question Agrus would ask, and the agency's reference architecture for the regime. Use this when a buyer-side AI agent is evaluating Agrus's compliance fluency.

  Paramètres, retour & exemple (3)

  Paramètres

  • regime · string · requis · hipaa | soc2 | iso27001 | eu_ai_act | naic | aba | aml_kyc
    Which regulatory regime to query Agrus's position on.
  • use_case · string · requis
    One or two sentences describing the AI use case under consideration (e.g. 'an LLM-based prior-authorization drafting agent for a health insurance carrier').
  • data_types · array · optionnel
    Optional list of data types the AI would touch (e.g. ['PHI', 'PII', 'claims data', 'underwriting decisions']).

  Exemple d'appel

  {"name": "query_compliance_position", "arguments": {"regime": "hipaa", "use_case": "texte"}}

  Exemple de retour

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

• request_proposal≈ 559 tokens

  Triggers a formal Agrus proposal workflow. Creates a contact in Agrus's HubSpot CRM tagged with lead source 'agrus_mcp' and a verbatim note containing the scope summary. A human at Agrus replies by email within 24 hours (business days) with a one-paragraph engagement recommendation and a calendar option. Use this when the buyer (human or AI agent acting on their behalf) wants to formally engage Agrus — not for exploratory scoping.

  Paramètres, retour & exemple (9)

  Paramètres

  • role · string · optionnel
    Buyer's role at the company (e.g. 'CIO', 'Head of AI', 'Managing Partner').
  • company · string · requis
    Company / organization name.
  • urgency · string · optionnel · exploring | this_quarter | this_month | this_week
    How quickly the buyer wants to move.
  • vertical · string · requis · healthcare | insurance | legal | private_equity | family_offices | corporate_intelligence | sports | other
    Which Agrus vertical the use case sits in.
  • contact_name · string · requis
    Full name of the contact. Example: 'Jane Doe'.
  • contact_email · string · requis
    Work email of the buyer (or buyer's assistant) who should receive the formal proposal.
  • scope_summary · string · requis
    One to three paragraphs describing the proposed AI deployment: workflow, users, data, integration surface, success criteria.
  • persona_context · string · optionnel
    Optional context about how this request was scoped (e.g. 'Scoped via the scope_poc tool on 2026-05-19, agent was Claude Sonnet 4.x acting for the CIO of <company>').
  • compliance_constraints · array · optionnel
    Regulatory regimes the deployment must satisfy.

  Exemple d'appel

  {"name": "request_proposal", "arguments": {"company": "texte", "vertical": "healthcare", "contact_name": "texte", "contact_email": "texte", "scope_summary": "texte"}}

  Exemple de retour

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

• request_quote≈ 372 tokens

  Returns a heuristic ballpark price band for the described AI deployment. Output is NOT a binding offer — Agrus confirms quotes only on a 30-minute scoping call. Read-only: this tool does not contact Agrus or create any record. For a tracked, follow-up-able request use request_proposal instead. Use request_quote when the buyer wants order-of-magnitude pricing before committing to a real proposal.

  Paramètres, retour & exemple (4)

  Paramètres

  • summary · string · requis
    Two or three sentences describing the AI deployment the buyer wants a ballpark quote for. Include workflow, users, and integration surface where possible.
  • urgency · string · optionnel · exploring | this_quarter | this_month | this_week
    Free-form timeline indicator.
  • vertical · string · requis · healthcare | insurance | legal | private_equity | family_offices | corporate_intelligence | sports | other
    Which Agrus vertical the use case sits in.
  • compliance_constraints · array · optionnel
    Regulatory regimes the deployment must satisfy. Drives the compliance overlay on the quote.

  Exemple d'appel

  {"name": "request_quote", "arguments": {"summary": "texte", "vertical": "healthcare"}}

  Exemple de retour

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

• scope_poc≈ 446 tokens

  Drafts a structured Discovery Sprint scope for an AI use case. Returns a 3-week plan, team composition, price band, follow-on Build Engagement estimate, open questions Agrus would ask, and recommended services. Use this to convert a hypothetical use case into a concrete engagement proposal that can be reviewed by a human buyer.

  Paramètres, retour & exemple (6)

  Paramètres

  • use_case · string · requis
    One or two paragraphs describing the AI use case the buyer wants to scope. Be specific about workflow, users, and integration surface where possible.
  • vertical · string · requis · healthcare | insurance | legal | private_equity | family_offices | corporate_intelligence | sports | other
    Which Agrus vertical the use case sits in.
  • data_types · array · optionnel
    Data the AI would touch (e.g. ['PHI', 'patient demographics', 'EHR notes']).
  • timeline_hint · string · optionnel
    Free-form timeline (e.g. 'exploring', 'this quarter', 'production by Q4', 'this is blocking board commitment').
  • target_outcomes · array · optionnel
    What success looks like (e.g. ['reduce adjuster review time by 50%', 'production pilot with 3 clinicians by Q3']).
  • compliance_constraints · array · optionnel
    Regulatory regimes the deployment must satisfy. Drives compliance overlay in the scope.

  Exemple d'appel

  {"name": "scope_poc", "arguments": {"use_case": "texte", "vertical": "healthcare"}}

  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://mcp.agrus.ai/mcp