com.adadiamonds/ada-diamonds

Est-ce que com.adadiamonds/ada-diamonds est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.adadiamonds/ada-diamonds » 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

• create_checkout_link≈ 1365 tokens

  Assemble a cart and get a Stripe-hosted checkout URL the customer opens to pay; no card data passes through the agent. Item ids come from the search tools (`diamond:<report>`, `setting:<slug>`, `jewelry:<slug>`); a complete ring is one setting plus one diamond. Needs the shipping address (prices tax and shipping into the link). Expires after 24 hours. No credential needed. Without a production credential this tool runs in the sandbox: the link is simulated and no Stripe session is created. Pass `env: "production"` when the customer actually wants to buy — that returns a live, payable link.

  Paramètres, retour & exemple (8)

  Paramètres

  • env · string · optionnel · production | sandbox
    sandbox returns a simulated link and creates no Stripe session; production mints a live, payable Stripe Checkout link. Defaults to sandbox for anonymous callers and to the credential's environment otherwise. A sandbox credential is always sandbox.
  • items · array · requis
    Items to buy; a complete ring is one setting plus one diamond
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • buyer_name · string · optionnel
    Buyer full name
  • buyer_email · string · optionnel
    Buyer email for the receipt; Stripe collects it on the payment page when omitted
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.
  • shipping_address · object · requis
    Where the order ships; used to price tax and shipping into the link

  Exemple d'appel

  {"name": "create_checkout_link", "arguments": {"items": [], "context": "texte", "llm_model": "texte", "shipping_address": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "status": "ready", "message": "texte", "sandbox": true, "tax_usd": 1, "problems": [], "total_usd": 1, "expires_at": "texte", "shipping_usd": 1, "subtotal_usd": 1}}

• get_company_info≈ 907 tokens

  Contact details, showroom address and hours, how consultations work, and what Ada Diamonds sells. Use this to answer questions about the business rather than about a product.

  Paramètres, retour & exemple (4)

  Paramètres

  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • section · string · optionnel · all | contact | showrooms | consultations
    Which part to return as text: contact (phone, email, hours, website), showrooms (addresses and hours), consultations (how remote and in-person consultations work), or all (default). The structured result always carries every section.
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "get_company_info", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "email": "texte", "hours": "texte", "phone": "texte", "website": "texte", "showrooms": [], "inquiryUrl": "texte", "description": "texte"}}

• read_article≈ 648 tokens

  Fetch the full markdown text of one Ada Diamonds knowledge base article by slug. Use search_knowledge_base first if you don't know the slug.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · requis
    Article slug from search_knowledge_base, e.g. "cvd-lab-diamonds" or "lab-diamond-shapes-guide"
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "read_article", "arguments": {"slug": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "slug": "texte", "found": true, "title": "texte", "excerpt": "texte", "markdown": "texte"}}

• request_consultation≈ 839 tokens

  Submit a consultation request on the customer's behalf. Requires the `appointments:write` scope, which the customer grants through Ada's OAuth authorization flow — this tool cannot be used without their explicit approval.

  Paramètres, retour & exemple (10)

  Paramètres

  • name · string · optionnel
    Customer's name
  • email · string · requis
    Customer's email address; the jeweler replies here
  • phone · string · optionnel
    Customer's phone number, if they want a call
  • topic · string · optionnel · engagement_ring | loose_diamond | wedding_band | fine_jewelry | custom_design | other
    What the consultation is about
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • message · string · optionnel
    What the customer is looking for, in their words
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • budget_usd · number · optionnel
    Approximate budget in US dollars
  • product_url · string · optionnel
    URL of a specific diamond, setting, or piece they are interested in
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "request_consultation", "arguments": {"email": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"email": "texte", "status": "received", "message": "texte", "sandbox": true, "reference": "texte"}}

• search_diamonds≈ 1345 tokens

  Search Ada Diamonds' live loose lab grown diamond inventory by shape, carat weight, price, color, clarity, and cut. Returns currently available stones with their grading report numbers and product URLs. Use this for any question about what diamond a budget can buy. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.

  Paramètres, retour & exemple (13)

  Paramètres

  • cut · string · optionnel
    Cut grade: Ideal, Excellent, or Very Good
  • sort · string · optionnel · price_asc | price_desc | carat_asc | carat_desc
    Result order: price_asc (default relevance), price_desc, carat_asc, or carat_desc
  • color · string · optionnel
    Color grade, D (colorless) through K
  • limit · number · optionnel
    Maximum number of results to return, 1 to 50 (default 10)
  • shape · string · optionnel
    Cut shape: Round, Oval, Cushion, Emerald, Pear, Radiant, Asscher, Princess, or Marquise
  • clarity · string · optionnel
    Clarity grade: FL, IF, VVS1, VVS2, VS1, VS2, SI1, or SI2
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • max_carat · number · optionnel
    Maximum carat weight, e.g. 2
  • max_price · number · optionnel
    Maximum price of the loose stone in US dollars
  • min_carat · number · optionnel
    Minimum carat weight, e.g. 1 or 1.5
  • min_price · number · optionnel
    Minimum price of the loose stone in US dollars
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "search_diamonds", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "items": [], "query": {}, "shown": 1, "total": 1, "browseUrl": "texte"}}

• search_engagement_rings≈ 1263 tokens

  Search Ada Diamonds' engagement ring settings by center-stone shape, style, and setting price. Setting prices exclude the center diamond — pair with search_diamonds to quote a complete ring. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.

  Paramètres, retour & exemple (10)

  Paramètres

  • q · string · optionnel
    Free-text match on the setting name
  • type · string · optionnel
    Setting type, e.g. Solitaire, Halo, Three Stone
  • limit · number · optionnel
    Maximum number of results to return, 1 to 50 (default 10)
  • shape · string · optionnel
    Center-stone shape the setting must accommodate, e.g. Oval
  • style · string · optionnel
    Design style, e.g. Petite Four Prong, Trellis, Bezel
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • max_price · number · optionnel
    Maximum setting price in US dollars, excluding the center diamond
  • min_price · number · optionnel
    Minimum setting price in US dollars, excluding the center diamond
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "search_engagement_rings", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "items": [], "query": {}, "shown": 1, "total": 1, "browseUrl": "texte"}}

• search_jewelry≈ 1210 tokens

  Search Ada Diamonds' fine jewelry — wedding bands, earrings, necklaces, bracelets, and fashion rings — by category, type, diamond shape, and price. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.

  Paramètres, retour & exemple (10)

  Paramètres

  • q · string · optionnel
    Free-text match on the product name
  • type · string · optionnel
    Type, e.g. Wedding Bands, Earrings, Necklaces, Bracelets, Rings
  • limit · number · optionnel
    Maximum number of results to return, 1 to 50 (default 10)
  • shape · string · optionnel
    Diamond shape used in the piece, e.g. Round
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • category · string · optionnel
    Category: Bridal or Fashion
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • max_price · number · optionnel
    Maximum price in US dollars
  • min_price · number · optionnel
    Minimum price in US dollars
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "search_jewelry", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "items": [], "query": {}, "shown": 1, "total": 1, "browseUrl": "texte"}}

• search_knowledge_base≈ 790 tokens

  Search Ada Diamonds' published guides on lab grown diamonds — the 4Cs, CVD vs HPHT growth, shape guides, certification, and buying advice. Returns article summaries and markdown URLs. Use read_article to get an article's full text.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Maximum number of results to return, 1 to 25 (default 8)
  • query · string · requis
    Topic to search for, matched against article titles, summaries, and slugs
  • context · string · requis
    Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
  • llm_model · string · requis
    The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
  • conversation_id · string · optionnel
    Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

  Exemple d'appel

  {"name": "search_knowledge_base", "arguments": {"query": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"kind": "texte", "items": [], "query": "texte", "total": 1, "browseUrl": "texte"}}

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://www.adadiamonds.com/mcp