accueil / serveurs / Recherche & Web / ai.servana/servana
ai.servana/servana
serveur MCP (Model Context Protocol) · servana 1.0.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que ai.servana/servana est sûr ?
Au dernier audit MCP Hub, le serveur MCP « ai.servana/servana » 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 8 outils
- check_enquiry_replies≈ 193 tokens
Use this when the user asks whether a business answered an enquiry sent earlier in this conversation with send_message_to_vendor. Pass the enquiry_refs that send_message_to_vendor returned. Returns, per business, whether it replied and the latest reply. Do not use for enquiries sent outside this conversation or without a ref; never guess a ref.
Paramètres, retour & exemple (1)
Paramètresenquiry_refs· array · requis
The enquiry_refs returned by send_message_to_vendor
Exemple d'appel{"name": "check_enquiry_replies", "arguments": {"enquiry_refs": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - estimate_service_request≈ 403 tokens
Use this when the user asks what a local service costs in a city (e.g. 'how much is a deep clean in NYC?'). Returns a rough range from Servana businesses' posted rates with a confidence level ('high' = 5+ local priced businesses, 'medium' = 2-4, 'low' = 0-1, then a category-wide median) and an explanation naming the sample. Always call it an estimate, never a quote: each business sets its own price. Do not use for one business's prices; use get_vendor.
Paramètres, retour & exemple (5)
Paramètrescity· string · requis
City name or slug (e.g. 'new-york', 'tampa', 'los-angeles'). For New York City use 'new-york'.hours· number · optionnel
Optional: estimated hours needed, if known. Overrides job_size for hourly-rate services.state· string · requis
US state, as a name or slug (e.g. 'new-york', 'florida'). Two-letter codes like 'NY' also work.service· string · requis
Service category slug: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photography', 'home-services' (handyman, home upkeep), 'personal-services'job_size· string · optionnel · small | medium | large
Rough size of the job. Defaults to 'medium'.
Exemple d'appel{"name": "estimate_service_request", "arguments": {"city": "texte", "state": "texte", "service": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_vendor≈ 158 tokens
Use this when the user asks about one specific business from search_vendors results or a servana.ai page: its services, prices, rating, claim status, and whether it accepts messages from AI assistants. Do not use to search for businesses.
Paramètres, retour & exemple (1)
Paramètresvendor_slug· string · requis
The vendor's slug from search_vendors results or a servana.ai vendor URL
Exemple d'appel{"name": "get_vendor", "arguments": {"vendor_slug": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - prepare_quote_request≈ 392 tokens
Use this when the user wants quotes or availability from 1 to 3 Servana businesses (slugs from search_vendors). It shows a quote request form with the details those businesses need (date, area, size and so on), pre-filled with what the user already said, so the user can check and send it. Prefer this over writing a free-text message. It sends nothing. Do not use for businesses that were not returned by search_vendors.
Paramètres, retour & exemple (6)
Paramètresnotes· string · optionnel
Anything else the user wants to saydetails· object · optionnel
What the user already said, keyed by field: date_window, time_window, area, home_size, job_details, frequency, session_goal, session_count, treatment, shoot_type, duration, people_count, load_size, budget. Leave out what you do not know; never invent.service· string · optionnel
Service category slug, e.g. 'cleaning-and-organizing'vendor_slugs· array · requis
1 to 3 business slugs from search_vendorscustomer_name· string · optionnel
The user's name, if they gave itcustomer_email· string · optionnel
The user's email, if they gave it
Exemple d'appel{"name": "prepare_quote_request", "arguments": {"vendor_slugs": []}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - request_quote≈ 312 tokens
Use this when the user approved a structured quote request to 1 to 3 Servana businesses (usually from the prepare_quote_request form). Servana formats the details the businesses asked for and emails the user their replies. If details are missing it returns which ones; ask the user, never invent. Do not use to book or pay; Servana does neither.
Paramètres, retour & exemple (7)
Paramètresnotes· string · optionneldetails· object · requis
Field values keyed by: date_window, time_window, area, home_size, job_details, frequency, session_goal, session_count, treatment, shoot_type, duration, people_count, load_size, budgetservice· string · optionnel
Service category slugvendor_slugs· array · requiscustomer_name· string · requiscustomer_email· string · requiscustomer_phone· string · optionnel
Exemple d'appel{"name": "request_quote", "arguments": {"details": {}, "vendor_slugs": [], "customer_name": "texte", "customer_email": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_services≈ 258 tokens
Use this when the user describes a local service they want done in person (e.g. 'someone to fold my laundry', 'deep clean my apartment', 'a trainer who comes to my home') and you need Servana's category slug for search_vendors or estimate_service_request. Skip it if the request clearly fits one of these slugs: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photography', 'home-services' (handyman, home upkeep), 'personal-services'. Do not use for online products, emergencies, or medical, legal or financial advice.
Paramètres, retour & exemple (1)
Paramètresquery· string · requis
Short description of the task the user needs done (a task, not a category name)
Exemple d'appel{"name": "search_services", "arguments": {"query": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_vendors≈ 466 tokens
Use this when the user wants to find, compare or hire a local business for an in-person service in a US city: house cleaners, laundry, med spas, yoga teachers, personal trainers, photographers, home services. Returns real businesses listed on Servana with rating, pricing when posted, claim status and a page URL. If it returns no results, tell the user Servana has no listed business for that yet; never invent one. Pass the user's specific need in `need` (e.g. decluttering, deep clean, packages) so the best-fitting businesses come first. Nearby towns are searched together (e.g. Nocatee with Ponte Vedra). Do not use for businesses outside the US or for services Servana does not list (use search_services if unsure).
Paramètres, retour & exemple (4)
Paramètrescity· string · requis
City name or slug (e.g. 'new-york', 'tampa', 'los-angeles'). For New York City use 'new-york'.need· string · optionnel
The user's specific need in their own words, e.g. 'declutter and organize a cluttered house, best packages'. Ranks businesses whose own description matches it first; never invents a match.state· string · requis
US state, as a name or slug (e.g. 'new-york', 'florida'). Two-letter codes like 'NY' also work.service· string · optionnel
Optional service category slug: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photography', 'home-services' (handyman, home upkeep), 'personal-services'. Use search_services if none fits.
Exemple d'appel{"name": "search_vendors", "arguments": {"city": "texte", "state": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - send_message_to_vendor≈ 487 tokens
Use this when the user has chosen a Servana business and asks you to contact it, request a quote, or ask about availability. It sends the user's enquiry to the business; Servana emails the user when the business replies. Pass customer_name and customer_email when the user gave them. To ask several businesses at once (up to 3), put the extra slugs in also_vendor_slugs. Keep the enquiry_refs it returns for check_enquiry_replies. Before calling, show the user the exact message and get their approval, and include their name and an email or phone number. Do not use to confirm a booking or take payment (Servana does neither), or for businesses marked as not accepting AI-assistant messages.
Paramètres, retour & exemple (6)
Paramètresmessage· string · requis
The enquiry: what the user needs, when and where, plus the user's name and preferred contact (email or phone) so the business can replyvendor_slug· string · requis
The vendor's slugcustomer_name· string · optionnel
The user's name, as they gave it. Needed so the business knows who is asking.customer_email· string · optionnel
The user's email, as they gave it. Servana emails the user a link to read the business's reply. Never invent one.customer_phone· string · optionnel
Optional phone number, only if the user gave one.also_vendor_slugs· array · optionnel
Optional: up to 2 more Servana businesses (slugs from search_vendors) to send the same enquiry to. Only when the user asked to contact several businesses and approved the one message for all of them.
Exemple d'appel{"name": "send_message_to_vendor", "arguments": {"message": "texte", "vendor_slug": "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 ».