org.singchat/singchat

Est-ce que org.singchat/singchat est sûr ?

Au dernier audit MCP Hub, le serveur MCP « org.singchat/singchat » 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 17 outils

• add_knowledge≈ 230 tokens

  Train the AI agent by adding a knowledge source. type='url' crawls a website (up to 50 pages, fewer when the workspace knowledge-base quota is nearly full); type='qa' stores a single question/answer pair. Ingestion is asynchronous, the source starts as PENDING; poll `list_knowledge` for READY status.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · optionnel
    Website root URL to crawl. Required when type='url'.
  • type · string · requis · url | qa
    'url' to crawl a website, or 'qa' to add a question/answer pair.
  • answer · string · optionnel
    The answer. Required when type='qa'.
  • question · string · optionnel
    The question. Required when type='qa'.

  Exemple d'appel

  {"name": "add_knowledge", "arguments": {"type": "url"}}

  Exemple de retour

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

• claim_account≈ 105 tokens

  Return the link to claim (permanently secure) this SingChat workspace by setting an email and password. Use this for workspaces that were auto-created via MCP so the user does not lose access. The link is single-use and expires after 15 minutes. Requires an authenticated legacy workspace.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "claim_account", "arguments": {}}

  Exemple de retour

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

• configure_agent≈ 282 tokens

  Configure this workspace's AI support agent. All fields are optional, only the fields you pass are updated; the rest keep their current values. Call with no fields to just read back the current configuration. Does not touch or return any API keys.

  Paramètres, retour & exemple (5)

  Paramètres

  • model · string · optionnel
    Chat model id, e.g. gpt-4o-mini.
  • enabled · boolean · optionnel
    Turn the automated AI agent on (true) or off (false).
  • providerMode · string · optionnel · platform | byok
    'platform' = platform-hosted keys (billed via AI credits); 'byok' = bring your own key.
  • systemPrompt · string · optionnel
    The agent's system prompt / persona and answering rules.
  • greetingMessage · string · optionnel
    First message visitors see when they open the chat. Pass an empty string to clear it.

  Exemple d'appel

  {"name": "configure_agent", "arguments": {"model": "texte", "enabled": true, "providerMode": "platform", "systemPrompt": "texte", "greetingMessage": "texte"}}

  Exemple de retour

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

• fetch≈ 235 tokens

  Fetch the full text of a single document by id, using an id returned by the search tool. With a workspace API key this reads a knowledge document from that workspace; without a key it reads a SingChat help article. Returns id, title, text, url, and optional metadata.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The document id returned by the search tool.

  Exemple d'appel

  {"name": "fetch", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "metadata": {}}}

• get_analytics≈ 134 tokens

  Return a compact analytics summary for this workspace over the last `days` days (default 30): conversation counts + resolution rate, message volume + AI share, plus a live snapshot of today (UTC).

  Paramètres, retour & exemple (1)

  Paramètres

  • days · integer · optionnel
    Look-back window in days for the conversation/message stats (default 30).

  Exemple d'appel

  {"name": "get_analytics", "arguments": {"days": 1}}

  Exemple de retour

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

• get_conversation≈ 108 tokens

  Fetch a single conversation with its contact details and the most recent messages (oldest→newest).

  Paramètres, retour & exemple (1)

  Paramètres

  • conversationId · string · requis
    The conversation id (from list_conversations).

  Exemple d'appel

  {"name": "get_conversation", "arguments": {"conversationId": "texte"}}

  Exemple de retour

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

• get_embed_snippet≈ 138 tokens

  Return the SingChat chat-widget embed code for this workspace's web inbox, in three flavors: plain HTML, React (useEffect), and Next.js (next/script). Requires a workspace API key. Optionally pass `platform` to get just one flavor.

  Paramètres, retour & exemple (1)

  Paramètres

  • platform · string · optionnel · html | react | next
    Which snippet to return. Omit to get all three.

  Exemple d'appel

  {"name": "get_embed_snippet", "arguments": {"platform": "html"}}

  Exemple de retour

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

• list_conversations≈ 211 tokens

  List the workspace's support conversations (agent/inbox view), newest activity first. Optionally filter by status or a free-text search over the contact name/email and last message. Returns a compact list: id, contact name, status, unreadCount, last message preview, updatedAt.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max conversations to return (default 100).
  • search · string · optionnel
    Free-text match on contact name/email and the last message preview.
  • status · string · optionnel · OPEN | PENDING | RESOLVED | SNOOZED
    Only conversations with this status.

  Exemple d'appel

  {"name": "list_conversations", "arguments": {"limit": 1, "search": "texte", "status": "OPEN"}}

  Exemple de retour

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

• list_knowledge≈ 85 tokens

  List all knowledge documents for this workspace with their processing status (PENDING | PROCESSING | READY | FAILED) and chunk counts. Use this to check whether items added via add_knowledge have finished training.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_knowledge", "arguments": {}}

  Exemple de retour

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

• manage_faq≈ 266 tokens

  List, create, update, or delete this workspace's FAQ items (shown in the chat widget and usable by the AI agent). Set `action` to 'list' | 'create' | 'update' | 'delete'. 'create' needs `question` + `answer`; 'update' and 'delete' need `id`.

  Paramètres, retour & exemple (5)

  Paramètres

  • id · string · optionnel
    FAQ item id. Required for 'update' and 'delete'.
  • action · string · requis · list | create | update | delete
    Which FAQ operation to run.
  • answer · string · optionnel
    Answer text. Required for 'create'; optional for 'update'.
  • enabled · boolean · optionnel
    Whether the FAQ item is visible/active. Optional for 'create' and 'update'.
  • question · string · optionnel
    Question text. Required for 'create'; optional for 'update'.

  Exemple d'appel

  {"name": "manage_faq", "arguments": {"action": "list"}}

  Exemple de retour

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

• ping≈ 55 tokens

  Health check for the SingChat MCP server. Returns 'pong' and whether this request is authenticated to a workspace.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "ping", "arguments": {}}

  Exemple de retour

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

• reply_to_conversation≈ 172 tokens

  Send an agent reply through a supported SingChat real-time inbox. This takes the conversation over from the AI and broadcasts the message to the visitor and agent inbox. Email, Telegram, and WhatsApp conversations are rejected before any change.

  Paramètres, retour & exemple (2)

  Paramètres

  • content · string · requis
    The reply text to send to the visitor.
  • conversationId · string · requis
    The conversation id to reply in.

  Exemple d'appel

  {"name": "reply_to_conversation", "arguments": {"content": "texte", "conversationId": "texte"}}

  Exemple de retour

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

• resolve_conversation≈ 106 tokens

  Mark a conversation as RESOLVED (closes it). The visitor's widget will no longer show it as active.

  Paramètres, retour & exemple (1)

  Paramètres

  • conversationId · string · requis
    The conversation id to resolve.

  Exemple d'appel

  {"name": "resolve_conversation", "arguments": {"conversationId": "texte"}}

  Exemple de retour

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

• search≈ 262 tokens

  Search SingChat for relevant documents. When called with a workspace API key, this searches that workspace knowledge base; without a key it searches SingChat's own help content (what SingChat is, adding the chat widget, MCP setup, free tier, AI training, channels, white label, pricing). Returns a list of results with id, title, and url. Use the fetch tool with a result id to read the full text.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    The search query or user question.

  Exemple d'appel

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

  Exemple de retour

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

• search_knowledge≈ 159 tokens

  Semantic search over the workspace knowledge base. Returns the most relevant chunks (with source document title and similarity score) for a query. Only searches documents that have finished training (status READY).

  Paramètres, retour & exemple (2)

  Paramètres

  • topK · integer · optionnel
    Max number of chunks to return (default 5).
  • query · string · requis
    The search query / user question.

  Exemple d'appel

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

  Exemple de retour

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

• set_keywords≈ 228 tokens

  Add a keyword auto-reply rule: when an inbound message matches any of the keywords, the bot replies with the given text. Good for canned FAQ-style triggers (e.g. keyword 'invoice' -> 'Download it from the billing page').

  Paramètres, retour & exemple (3)

  Paramètres

  • reply · string · requis
    The reply text to send.
  • keywords · array · requis
    Trigger words/phrases (case-insensitive).
  • matchType · string · optionnel · CONTAINS | EXACT
    CONTAINS (default) = keyword appears anywhere in the message; EXACT = whole message equals the keyword.

  Exemple d'appel

  {"name": "set_keywords", "arguments": {"reply": "texte", "keywords": []}}

  Exemple de retour

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

• singchat_setup≈ 208 tokens

  Get the user up and running with SingChat live-chat. Call this FIRST. If no authenticated workspace is configured, this creates a brand-new free workspace and returns a short-lived, single-use browser claim link plus the website embed snippet. The user chooses their own sign-in details in the browser; no reusable credentials are returned to the model. If a workspace is already authenticated, it returns THIS workspace's embed snippet and dashboard link (it never creates a duplicate workspace).

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · optionnel
    Optional workspace/brand name for a newly created workspace. Ignored if a key is already set.

  Exemple d'appel

  {"name": "singchat_setup", "arguments": {"name": "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://mcp.singchat.org