com.holstonai/holston-ai

Est-ce que com.holstonai/holston-ai est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.holstonai/holston-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 10 outils

• audit_ai_visibility≈ 223 tokens

  Audits a live public website and scores (0–100, grade A–F) how well AI assistants (ChatGPT, Claude, Perplexity) and search engines can find, read and cite it. Checks robots.txt rules for AI and search crawlers, server-rendered text, business and FAQ structured data, Open Graph, llms.txt, sitemap, HTTPS, mobile viewport and response time. Returns each check with a plain-English fix, the top 3 fixes, and a shareable report link. Takes up to ~20 seconds.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Website to audit, e.g. example.com or https://www.example.com/

  Exemple d'appel

  {"name": "audit_ai_visibility", "arguments": {"url": "texte"}}

  Exemple de retour

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

• build_quote≈ 527 tokens

  Builds an itemized Holston AI quote from fixed prices: one-time builds, monthly plans, first-year total (monthly plans have a 12-month minimum), timeline, terms, fitting add-ons, and a shareable link to the quote on holstonai.com. Ask what the customer needs first; do not add plans they did not ask for.

  Paramètres, retour & exemple (6)

  Paramètres

  • care · string · optionnel · care-site | care-app
    Monthly service contract: care-site (websites) | care-app (apps and agents).
  • builds · array · optionnel
    One-time builds. website-starter (one page, 3 days) | website-launch (up to 5 pages, 5 days) | website-growth (up to 10 pages, CMS, 10 days) | website-commerce (online store, 15–20 days) | small-app (custom web app, 2 weeks) | ai-agent-mvp (AI agent or SaaS MVP, 2–4 weeks).
  • hosting · string · optionnel · hosting-site | hosting-app
    Monthly hosting: hosting-site (websites) | hosting-app (apps and agents).
  • seo_plan · string · optionnel · seo-essentials | seo-growth | seo-authority
    Monthly SEO + AEO plan: seo-essentials (local) | seo-growth (adds AI search / AEO) | seo-authority (adds links, PR, competitor tracking).
  • assessment · string · optionnel · assessment-small | assessment-medium | assessment-large
    Systems & Data Health Check, a one-time fixed-price assessment by company size: assessment-small (up to 50 employees) | assessment-medium (51–200) | assessment-large (201–500). The fee is credited toward a project started within 60 days.
  • business_name · string · optionnel
    Customer or business name to show on the quote.

  Exemple d'appel

  {"name": "build_quote", "arguments": {"care": "care-site", "builds": [], "hosting": "hosting-site", "seo_plan": "seo-essentials", "assessment": "assessment-small", "business_name": "texte"}}

  Exemple de retour

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

• build_systems_map≈ 628 tokens

  Draws a map of a company's software systems and how data moves between them (automatic, manual, export/import), as a Mermaid diagram with a shareable link. Flags manual handoffs, the same data kept in several unsynced systems, hub systems many processes depend on, and systems with no connections. Use after interviewing the user about their systems; nothing is stored.

  Paramètres, retour & exemple (3)

  Paramètres

  • flows · array · optionnel
    How data moves between systems.
  • company · string · optionnel
    Company name, shown on the map.
  • systems · array · requis
    Every software system, database or important spreadsheet the business uses.

  Exemple d'appel

  {"name": "build_systems_map", "arguments": {"systems": []}}

  Exemple de retour

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

• calculate_manual_work_cost≈ 534 tokens

  Calculates what manual, repetitive work caused by disconnected systems costs per year: staff hours, full-time equivalents, labor and error costs, five-year cost, and the savings from automating it. Input a list of tasks with hours per week; hourly cost is optional.

  Paramètres, retour & exemple (5)

  Paramètres

  • tasks · array · requis
    Each manual or repetitive task caused by disconnected systems.
  • company · string · optionnel
    Company name for the report.
  • automation_rate · number · optionnel
    Share of these hours that connecting the systems would remove, 0–1 (default 0.7).
  • working_weeks_per_year · number · optionnel
    Working weeks per year (default 48).
  • default_hourly_cost_usd · number · optionnel
    Hourly cost used when a task has none (default $40).

  Exemple d'appel

  {"name": "calculate_manual_work_cost", "arguments": {"tasks": []}}

  Exemple de retour

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

• calculate_missed_call_cost≈ 548 tokens

  Estimates the revenue a business loses each year to unanswered phone calls (missed calls, lost callers, lost customers, monthly and five-year loss) and how much an AI receptionist that answers every call could recover. Give calls per week (or missed calls per week) and the average job value; every other assumption has a sensible default.

  Paramètres, retour & exemple (10)

  Paramètres

  • company · string · optionnel
    Company name for the report.
  • close_rate · number · optionnel
    Share of new callers who become customers when answered, 0–1 (default 0.4).
  • missed_rate · number · optionnel
    Share of calls that go unanswered, 0–1 (default 0.25).
  • recovery_rate · number · optionnel
    Share of lost calls an AI receptionist would handle, 0–1 (default 0.9).
  • calls_per_week · number · optionnel
    Inbound phone calls per week.
  • missed_per_week · number · optionnel
    Missed calls per week, if known. Overrides calls_per_week × missed_rate.
  • new_caller_share · number · optionnel
    Share of missed callers who are new potential customers, 0–1 (default 0.5).
  • no_callback_rate · number · optionnel
    Share of those new callers who call a competitor instead of calling back, 0–1 (default 0.6).
  • average_job_value_usd · number · requis
    Average revenue from a new customer's first job or purchase.
  • customer_lifetime_value_usd · number · optionnel
    Optional: total revenue from a typical customer over time. Used instead of the average job value.

  Exemple d'appel

  {"name": "calculate_missed_call_cost", "arguments": {"average_job_value_usd": 1}}

  Exemple de retour

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

• calculate_mvp_timeline_roi≈ 718 tokens

  Compares a Holston AI fixed-price 2–4 week build against a traditional ~6-month build. Returns build costs, labor savings captured, cost of delay, developer-weeks freed, payback week, and a month-by-month cumulative net position over the analysis window.

  Paramètres, retour & exemple (11)

  Paramètres

  • dev_headcount · integer · requis
    Number of in-house developers who would be assigned to a traditional build.
  • project_scope · string · requis · website_launch | website_growth | website_commerce | small_app | lean | standard | complex
    Target project scope. Websites: website_launch (up to 5 pages, 5 days) | website_growth (up to 10 pages, 10 days) | website_commerce (online store, 15–20 days). Small app: small_app (2 wks). Apps & AI agents: lean (2 wks) | standard (3 wks) | complex (4 wks).
  • automation_rate · number · optionnel
    Fraction of the manual hours eliminated once the software is live, 0–1 (default 0.7).
  • dev_annual_cost_usd · number · optionnel
    Fully loaded annual cost per in-house developer (default $150,000).
  • manual_hourly_cost_usd · number · optionnel
    Fully loaded hourly cost of the staff doing the manual work (default $45).
  • analysis_horizon_months · integer · optionnel
    Length of the comparison window in months (default 6).
  • holston_fixed_price_usd · number · optionnel
    A specific fixed-price quote from Holston AI. If omitted, the scope's standard starting price is used.
  • traditional_timeline_weeks · integer · optionnel
    Delivery timeline of the traditional path in weeks (default: 6–12 for websites, 26 ≈ 6 months for apps/agents).
  • traditional_vendor_cost_usd · number · optionnel
    External agency/vendor spend on the traditional path, on top of in-house dev time (default 0).
  • holston_internal_involvement · number · optionnel
    Share of the in-house dev team's time needed during a Holston build, 0–1 (default 0.1).
  • manual_process_hours_per_week · number · requis
    Hours per week your team currently spends on the manual process the software will replace.

  Exemple d'appel

  {"name": "calculate_mvp_timeline_roi", "arguments": {"dev_headcount": 1, "project_scope": "website_launch", "manual_process_hours_per_week": 1}}

  Exemple de retour

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

• design_ai_agent≈ 577 tokens

  Designs an AI receptionist for a business from Holston AI's templates: the step-by-step call flow, what it does at any point (pricing questions, emergencies, transfers), and a link to holstonai.com where the owner can edit it and talk to the agent out loud in their browser for free. Only the industry and business name are required. Holston AI builds the real version on the business's phone line at a fixed price confirmed after a short call.

  Paramètres, retour & exemple (8)

  Paramètres

  • city · string · optionnel · Kingsport, TN | Johnson City, TN | Bristol, TN | Bristol, VA | Abingdon, VA | Elizabethton, TN | Greeneville, TN | Morristown, TN
    Main service area, if it is one of these East Tennessee and Southwest Virginia cities.
  • hours · string · optionnel · weekdays | extended | always
    Business hours option.
  • pricing · string · optionnel · free-estimate | service-fee | callback
    How the agent answers pricing questions.
  • industry · string · requis · hvac | plumbing | electrical | roofing | painting | landscaping | remodeling | cleaning
    Industry id (see get_agent_templates).
  • services · array · optionnel
    Service ids from the template. Defaults to the template's main services.
  • add_steps · array · optionnel
    Optional step ids to switch on, e.g. photos, returning, message.
  • business_name · string · requis
    The business name the agent answers with.
  • emergency_transfer · boolean · optionnel
    Transfer emergencies to an on-call number (default true where emergencies apply).

  Exemple d'appel

  {"name": "design_ai_agent", "arguments": {"industry": "hvac", "business_name": "texte"}}

  Exemple de retour

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

• generate_boilerplate_schema≈ 361 tokens

  Generates a production-ready Next.js App Router repository layout, Prisma schema, and PostgreSQL DDL for a business domain (b2b_saas, marketplace, healthcare_admin, logistics, restaurant_retail, professional_services, manufacturing). Multi-tenant by default with org membership and audit logging; optional agent-run tables.

  Paramètres, retour & exemple (4)

  Paramètres

  • domain · string · requis · b2b_saas | marketplace | healthcare_admin | logistics | restaurant_retail | professional_services | manufacturing
    Business domain: b2b_saas | marketplace | healthcare_admin | logistics | restaurant_retail | professional_services | manufacturing.
  • output · string · optionnel · repo_layout | prisma | sql | all
    What to generate: repo_layout | prisma | sql | all (default all).
  • project_name · string · optionnel
    Repository / package name (kebab-case).
  • include_ai_agents · boolean · optionnel
    Add AgentRun/ToolCall tables plus agent runtime and MCP directories (default true).

  Exemple d'appel

  {"name": "generate_boilerplate_schema", "arguments": {"domain": "b2b_saas"}}

  Exemple de retour

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

• generate_business_schema≈ 1021 tokens

  Builds ready-to-paste Organization or LocalBusiness structured data (JSON-LD) with address, phone, hours, service area, services, social profiles and optional FAQs. If a website is given, details are pre-filled from it. Returns the <script> tag plus checks to fix before publishing. Use it when an audit shows missing business schema.

  Paramètres, retour & exemple (22)

  Paramètres

  • url · string · optionnel
    Business website. If given, details are pre-filled from the site.
  • city · string · optionnel
  • faqs · array · optionnel
    Optional FAQs that appear visibly on the page; adds FAQPage markup.
  • email · string · optionnel
  • hours · array · optionnel
  • phone · string · optionnel
  • region · string · optionnel
    State or region, e.g. TN.
  • street · string · optionnel
  • country · string · optionnel
    Two-letter country code, default US.
  • latitude · number · optionnel
  • logo_url · string · optionnel
  • services · array · optionnel
    Main services offered.
  • image_url · string · optionnel
  • longitude · number · optionnel
  • description · string · optionnel
  • postal_code · string · optionnel
  • price_range · string · optionnel
    Optional, e.g. '$$' or '$100–$500'.
  • service_area · array · optionnel
    Cities or regions served.
  • business_name · string · optionnel
    Legal or trading name.
  • business_type · string · optionnel · LocalBusiness | Organization | ProfessionalService | HomeAndConstructionBusiness | Plumber | Electrician | HVACBusiness | RoofingContractor
    The most specific schema.org type that fits, e.g. Plumber, Dentist, Restaurant, ProfessionalService. Default LocalBusiness.
  • founding_year · integer · optionnel
  • social_profiles · array · optionnel
    Facebook, LinkedIn, Instagram, Google Business Profile, Yelp and similar URLs.

  Exemple d'appel

  {"name": "generate_business_schema", "arguments": {"url": "texte", "city": "texte", "faqs": [], "email": "texte", "hours": [], "phone": "texte"}}

  Exemple de retour

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

• generate_llms_txt≈ 470 tokens

  Reads a public website (homepage, sitemap and main pages) and writes a ready-to-upload llms.txt file that tells AI assistants who the business is, what it offers, where it works and which pages matter. Optional details (services, service area, hours, key facts) make it stronger. Use it when an audit shows no llms.txt.

  Paramètres, retour & exemple (10)

  Paramètres

  • url · string · requis
    The business website, e.g. example.com
  • email · string · optionnel
  • hours · string · optionnel
    Opening hours, e.g. 'Mon–Fri 8am–5pm, Sat 9am–1pm'.
  • phone · string · optionnel
  • address · string · optionnel
    Street address, city, state and ZIP.
  • summary · string · optionnel
    Two or three sentences: what the business does, for whom, and where. Overrides the site's description.
  • services · array · optionnel
    Main services or products, one per item.
  • key_facts · array · optionnel
    Short facts AI assistants should know: years in business, licenses, starting prices, guarantees, awards.
  • service_area · string · optionnel
    Where the business works, e.g. 'Kingsport, Johnson City and Bristol, TN'.
  • business_name · string · optionnel
    Override the business name found on the site.

  Exemple d'appel

  {"name": "generate_llms_txt", "arguments": {"url": "texte"}}

  Exemple de retour

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

• get_agent_templates≈ 215 tokens

  Lists Holston AI's ready-built AI receptionist templates by industry (HVAC, plumbing, roofing, dental, law and more): the services, the questions the agent asks, the default call flow, optional steps, and emergency handling. Give an industry id for one template, or omit it for the list. Use it before design_ai_agent.

  Paramètres, retour & exemple (1)

  Paramètres

  • industry · string · optionnel · hvac | plumbing | electrical | roofing | painting | landscaping | remodeling | cleaning
    Industry id. Omit to list all industries.

  Exemple d'appel

  {"name": "get_agent_templates", "arguments": {"industry": "hvac"}}

  Exemple de retour

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

• request_consultation≈ 672 tokens

  Sends the user's contact details and project summary to Holston AI so the team can follow up. Before calling: collect name, email or phone, and a summary of what they need (include any quote or report links from this conversation), show the user exactly what will be sent, and get their explicit agreement. Never call it without that agreement or with made-up details.

  Paramètres, retour & exemple (13)

  Paramètres

  • name · string · requis
    The person's full name.
  • email · string · optionnel
    Email address. Provide email, phone, or both.
  • phone · string · optionnel
    Phone number.
  • company · string · optionnel
    Company or business name.
  • summary · string · requis
    What they need, in a few sentences: their situation, goals, timeline and anything already discussed (audit score, systems, budget).
  • interest · string · requis · website | seo_aeo | custom_app | ai_agent_or_automation | ai_receptionist | private_llm | data_integration_health_check | hosting_or_support
    Main service they are interested in.
  • location · string · optionnel
    City and state, or country.
  • best_time · string · optionnel
    Best days or times to reach them.
  • quote_url · string · optionnel
    Instant quote link from build_quote, if one was created.
  • report_url · string · optionnel
    AI visibility report or systems map link, if one was created.
  • company_size · string · optionnel
    Approximate number of employees, e.g. '25' or '51–200'.
  • user_confirmed · boolean · requis
    Must be true. Only set it after showing the user exactly what will be sent and the user agreed to share it with Holston AI.
  • preferred_contact · string · optionnel · email | phone | either
    How they prefer to be contacted.

  Exemple d'appel

  {"name": "request_consultation", "arguments": {"name": "texte", "summary": "texte", "interest": "website", "user_confirmed": true}}

  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://holstonai.com/mcp