SingChat

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

{
  "type": "object",
  "properties": {}
}

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).

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Optional workspace/brand name for a newly created workspace. Ignored if a key is already set.",
      "type": "string",
      "maxLength": 120
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {
    "platform": {
      "description": "Which snippet to return. Omit to get all three.",
      "type": "string",
      "enum": [
        "html",
        "react",
        "next"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {}
}

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.

{
  "type": "object",
  "properties": {
    "status": {
      "description": "Only conversations with this status.",
      "type": "string",
      "enum": [
        "OPEN",
        "PENDING",
        "RESOLVED",
        "SNOOZED"
      ]
    },
    "search": {
      "description": "Free-text match on contact name/email and the last message preview.",
      "type": "string"
    },
    "limit": {
      "description": "Max conversations to return (default 100).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 200
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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

{
  "type": "object",
  "properties": {
    "conversationId": {
      "type": "string",
      "minLength": 1,
      "description": "The conversation id (from list_conversations)."
    }
  },
  "required": [
    "conversationId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {
    "conversationId": {
      "type": "string",
      "minLength": 1,
      "description": "The conversation id to reply in."
    },
    "content": {
      "type": "string",
      "minLength": 1,
      "description": "The reply text to send to the visitor."
    }
  },
  "required": [
    "conversationId",
    "content"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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

{
  "type": "object",
  "properties": {
    "conversationId": {
      "type": "string",
      "minLength": 1,
      "description": "The conversation id to resolve."
    }
  },
  "required": [
    "conversationId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "url",
        "qa"
      ],
      "description": "'url' to crawl a website, or 'qa' to add a question/answer pair."
    },
    "url": {
      "description": "Website root URL to crawl. Required when type='url'.",
      "type": "string",
      "format": "uri"
    },
    "question": {
      "description": "The question. Required when type='qa'.",
      "type": "string"
    },
    "answer": {
      "description": "The answer. Required when type='qa'.",
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {}
}

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).

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "The search query / user question."
    },
    "topK": {
      "description": "Max number of chunks to return (default 5).",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {
    "enabled": {
      "description": "Turn the automated AI agent on (true) or off (false).",
      "type": "boolean"
    },
    "systemPrompt": {
      "description": "The agent's system prompt / persona and answering rules.",
      "type": "string",
      "minLength": 1,
      "maxLength": 8000
    },
    "greetingMessage": {
      "description": "First message visitors see when they open the chat. Pass an empty string to clear it.",
      "type": "string",
      "maxLength": 2000
    },
    "model": {
      "description": "Chat model id, e.g. gpt-4o-mini.",
      "type": "string",
      "minLength": 1,
      "maxLength": 80
    },
    "providerMode": {
      "description": "'platform' = platform-hosted keys (billed via AI credits); 'byok' = bring your own key.",
      "type": "string",
      "enum": [
        "platform",
        "byok"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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').

{
  "type": "object",
  "properties": {
    "keywords": {
      "minItems": 1,
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 80
      },
      "description": "Trigger words/phrases (case-insensitive)."
    },
    "reply": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The reply text to send."
    },
    "matchType": {
      "description": "CONTAINS (default) = keyword appears anywhere in the message; EXACT = whole message equals the keyword.",
      "type": "string",
      "enum": [
        "CONTAINS",
        "EXACT"
      ]
    }
  },
  "required": [
    "keywords",
    "reply"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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`.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "create",
        "update",
        "delete"
      ],
      "description": "Which FAQ operation to run."
    },
    "id": {
      "description": "FAQ item id. Required for 'update' and 'delete'.",
      "type": "string"
    },
    "question": {
      "description": "Question text. Required for 'create'; optional for 'update'.",
      "type": "string",
      "minLength": 1,
      "maxLength": 500
    },
    "answer": {
      "description": "Answer text. Required for 'create'; optional for 'update'.",
      "type": "string",
      "minLength": 1,
      "maxLength": 4000
    },
    "enabled": {
      "description": "Whether the FAQ item is visible/active. Optional for 'create' and 'update'.",
      "type": "boolean"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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).

{
  "type": "object",
  "properties": {
    "days": {
      "default": 30,
      "description": "Look-back window in days for the conversation/message stats (default 30).",
      "type": "integer",
      "minimum": 1,
      "maximum": 365
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The search query or user question."
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

{
  "type": "object",
  "properties": {
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "title",
          "url"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "results"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

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.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The document id returned by the search tool."
    }
  },
  "required": [
    "id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "url": {
      "type": "string"
    },
    "metadata": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": "string"
      }
    }
  },
  "required": [
    "id",
    "title",
    "text",
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}