SingChat is an MCP server published by org.singchat, hosted at mcp.singchat.org. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 17 tools, including ping, singchat_setup, get_embed_snippet, claim_account, list_conversations.
Free live chat and AI support agent. Auto-create a workspace and embed from your AI editor.
1 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Health check for the SingChat MCP server. Returns 'pong' and whether this request is authenticated to a workspace.
No parameters.
{
"name": "ping",
"title": "Ping",
"description": "Health check for the SingChat MCP server. Returns 'pong' and whether this request is authenticated to a workspace.",
"inputSchema": {
"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).
| Parameter | Type | Description |
|---|---|---|
| name | string | Optional workspace/brand name for a newly created workspace. Ignored if a key is already set. |
{
"name": "singchat_setup",
"title": "Set up SingChat",
"description": "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).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"description": "Optional workspace/brand name for a newly created workspace. Ignored if a key is already set."
}
}
}
}Return the SingChat chat-widget embed code for this workspace's web inbox, in three flavors: plain HTML, React (useEffect), and Next.js (next/script). Requires a workspace API key. Optionally pass `platform` to get just one flavor.
| Parameter | Type | Description |
|---|---|---|
| platform | string | Which snippet to return. Omit to get all three. |
{
"name": "get_embed_snippet",
"title": "Get widget embed snippet",
"description": "Return the SingChat chat-widget embed code for this workspace's web inbox, in three flavors: plain HTML, React (useEffect), and Next.js (next/script). Requires a workspace API key. Optionally pass `platform` to get just one flavor.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"platform": {
"enum": [
"html",
"react",
"next"
],
"type": "string",
"description": "Which snippet to return. Omit to get all three."
}
}
}
}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.
No parameters.
{
"name": "claim_account",
"title": "Claim SingChat account",
"description": "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.",
"inputSchema": {
"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.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max conversations to return (default 100). |
| search | string | Free-text match on contact name/email and the last message preview. |
| status | string | Only conversations with this status. |
{
"name": "list_conversations",
"title": "List conversations",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 200,
"description": "Max conversations to return (default 100).",
"exclusiveMinimum": 0
},
"search": {
"type": "string",
"description": "Free-text match on contact name/email and the last message preview."
},
"status": {
"enum": [
"OPEN",
"PENDING",
"RESOLVED",
"SNOOZED"
],
"type": "string",
"description": "Only conversations with this status."
}
}
}
}Fetch a single conversation with its contact details and the most recent messages (oldest→newest).
| Parameter | Type | Description |
|---|---|---|
| conversationId * | string | The conversation id (from list_conversations). |
{
"name": "get_conversation",
"title": "Get conversation",
"description": "Fetch a single conversation with its contact details and the most recent messages (oldest→newest).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"conversationId"
],
"properties": {
"conversationId": {
"type": "string",
"minLength": 1,
"description": "The conversation id (from list_conversations)."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| content * | string | The reply text to send to the visitor. |
| conversationId * | string | The conversation id to reply in. |
{
"name": "reply_to_conversation",
"title": "Reply to conversation",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"conversationId",
"content"
],
"properties": {
"content": {
"type": "string",
"minLength": 1,
"description": "The reply text to send to the visitor."
},
"conversationId": {
"type": "string",
"minLength": 1,
"description": "The conversation id to reply in."
}
}
}
}Mark a conversation as RESOLVED (closes it). The visitor's widget will no longer show it as active.
| Parameter | Type | Description |
|---|---|---|
| conversationId * | string | The conversation id to resolve. |
{
"name": "resolve_conversation",
"title": "Resolve conversation",
"description": "Mark a conversation as RESOLVED (closes it). The visitor's widget will no longer show it as active.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"conversationId"
],
"properties": {
"conversationId": {
"type": "string",
"minLength": 1,
"description": "The conversation id to resolve."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| url | string | Website root URL to crawl. Required when type='url'. |
| type * | string | 'url' to crawl a website, or 'qa' to add a question/answer pair. |
| answer | string | The answer. Required when type='qa'. |
| question | string | The question. Required when type='qa'. |
{
"name": "add_knowledge",
"title": "Add knowledge",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"type"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Website root URL to crawl. Required when type='url'."
},
"type": {
"enum": [
"url",
"qa"
],
"type": "string",
"description": "'url' to crawl a website, or 'qa' to add a question/answer pair."
},
"answer": {
"type": "string",
"description": "The answer. Required when type='qa'."
},
"question": {
"type": "string",
"description": "The question. Required when type='qa'."
}
}
}
}List all knowledge documents for this workspace with their processing status (PENDING | PROCESSING | READY | FAILED) and chunk counts. Use this to check whether items added via add_knowledge have finished training.
No parameters.
{
"name": "list_knowledge",
"title": "List knowledge",
"description": "List all knowledge documents for this workspace with their processing status (PENDING | PROCESSING | READY | FAILED) and chunk counts. Use this to check whether items added via add_knowledge have finished training.",
"inputSchema": {
"type": "object",
"properties": {}
}
}Semantic search over the workspace knowledge base. Returns the most relevant chunks (with source document title and similarity score) for a query. Only searches documents that have finished training (status READY).
| Parameter | Type | Description |
|---|---|---|
| topK | integer | Max number of chunks to return (default 5). |
| query * | string | The search query / user question. |
{
"name": "search_knowledge",
"title": "Search knowledge",
"description": "Semantic search over the workspace knowledge base. Returns the most relevant chunks (with source document title and similarity score) for a query. Only searches documents that have finished training (status READY).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"topK": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Max number of chunks to return (default 5)."
},
"query": {
"type": "string",
"minLength": 1,
"description": "The search query / user question."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| model | string | Chat model id: 'gpt-6-luna' (default, OpenAI) or 'claude-sonnet-5-5' (Anthropic, only when the platform has enabled it). |
| enabled | boolean | Turn the automated AI agent on (true) or off (false). |
| providerMode | string | 'platform' = platform-hosted keys (billed via AI credits); 'byok' = bring your own key. |
| systemPrompt | string | The agent's system prompt / persona and answering rules. |
| greetingMessage | string | First message visitors see when they open the chat. Pass an empty string to clear it. |
{
"name": "configure_agent",
"title": "Configure AI agent",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"model": {
"enum": [
"gpt-6-luna",
"claude-sonnet-5-5"
],
"type": "string",
"description": "Chat model id: 'gpt-6-luna' (default, OpenAI) or 'claude-sonnet-5-5' (Anthropic, only when the platform has enabled it)."
},
"enabled": {
"type": "boolean",
"description": "Turn the automated AI agent on (true) or off (false)."
},
"providerMode": {
"enum": [
"platform",
"byok"
],
"type": "string",
"description": "'platform' = platform-hosted keys (billed via AI credits); 'byok' = bring your own key."
},
"systemPrompt": {
"type": "string",
"maxLength": 8000,
"minLength": 1,
"description": "The agent's system prompt / persona and answering rules."
},
"greetingMessage": {
"type": "string",
"maxLength": 2000,
"description": "First message visitors see when they open the chat. Pass an empty string to clear it."
}
}
}
}Add a keyword auto-reply rule: when an inbound message matches any of the keywords, the bot replies with the given text. Good for canned FAQ-style triggers (e.g. keyword 'invoice' -> 'Download it from the billing page').
| Parameter | Type | Description |
|---|---|---|
| reply * | string | The reply text to send. |
| keywords * | array | Trigger words/phrases (case-insensitive). |
| matchType | string | CONTAINS (default) = keyword appears anywhere in the message; EXACT = whole message equals the keyword. |
{
"name": "set_keywords",
"title": "Add keyword auto-reply",
"description": "Add a keyword auto-reply rule: when an inbound message matches any of the keywords, the bot replies with the given text. Good for canned FAQ-style triggers (e.g. keyword 'invoice' -> 'Download it from the billing page').",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"keywords",
"reply"
],
"properties": {
"reply": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "The reply text to send."
},
"keywords": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"maxItems": 20,
"minItems": 1,
"description": "Trigger words/phrases (case-insensitive)."
},
"matchType": {
"enum": [
"CONTAINS",
"EXACT"
],
"type": "string",
"description": "CONTAINS (default) = keyword appears anywhere in the message; EXACT = whole message equals the keyword."
}
}
}
}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`.
| Parameter | Type | Description |
|---|---|---|
| id | string | FAQ item id. Required for 'update' and 'delete'. |
| action * | string | Which FAQ operation to run. |
| answer | string | Answer text. Required for 'create'; optional for 'update'. |
| enabled | boolean | Whether the FAQ item is visible/active. Optional for 'create' and 'update'. |
| question | string | Question text. Required for 'create'; optional for 'update'. |
{
"name": "manage_faq",
"title": "Manage FAQ",
"description": "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`.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"action"
],
"properties": {
"id": {
"type": "string",
"description": "FAQ item id. Required for 'update' and 'delete'."
},
"action": {
"enum": [
"list",
"create",
"update",
"delete"
],
"type": "string",
"description": "Which FAQ operation to run."
},
"answer": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "Answer text. Required for 'create'; optional for 'update'."
},
"enabled": {
"type": "boolean",
"description": "Whether the FAQ item is visible/active. Optional for 'create' and 'update'."
},
"question": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Question text. Required for 'create'; optional for 'update'."
}
}
}
}Return a compact analytics summary for this workspace over the last `days` days (default 30): conversation counts + resolution rate, message volume + AI share, plus a live snapshot of today (UTC). `resolved`, `resolutionRatePct` and `avgResolutionHours` exclude conversations closed by auto-resolve; `autoResolved` counts those separately and `resolvedIncludingAuto` is the total including them.
| Parameter | Type | Description |
|---|---|---|
| days | integer | Look-back window in days for the conversation/message stats (default 30). |
{
"name": "get_analytics",
"title": "Get Analytics",
"description": "Return a compact analytics summary for this workspace over the last `days` days (default 30): conversation counts + resolution rate, message volume + AI share, plus a live snapshot of today (UTC). `resolved`, `resolutionRatePct` and `avgResolutionHours` exclude conversations closed by auto-resolve; `autoResolved` counts those separately and `resolvedIncludingAuto` is the total including them.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"days": {
"type": "integer",
"default": 30,
"maximum": 365,
"minimum": 1,
"description": "Look-back window in days for the conversation/message stats (default 30)."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| query * | string | The search query or user question. |
{
"name": "search",
"title": "Search",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "The search query or user question."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"results"
],
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"title",
"url"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string"
},
"title": {
"type": "string"
}
},
"additionalProperties": false
}
}
},
"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.
| Parameter | Type | Description |
|---|---|---|
| id * | string | The document id returned by the search tool. |
{
"name": "fetch",
"title": "Fetch",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The document id returned by the search tool."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id",
"title",
"text",
"url"
],
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string"
},
"text": {
"type": "string"
},
"title": {
"type": "string"
},
"metadata": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"additionalProperties": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.