SingChat
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Free live chat and AI support agent. Auto-create a workspace and embed from your AI editor.
| Author | org.singchat |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2681 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"SingChat": {
"url": "https://mcp.singchat.org",
"transport": "streamable-http"
}
}
}
Measured tools (17)
pingHealth check for the SingChat MCP server. Returns 'pong' and whether this request is authenticated to a workspace.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
singchat_setupGet 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).
Parameters:
name— string — Optional workspace/brand name for a newly created workspace. Ignored if a key is already set.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_embed_snippetReturn 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.
Parameters:
platform— string — Which snippet to return. Omit to get all three.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
claim_accountReturn 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.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_conversationsList 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.
Parameters:
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.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_conversationFetch a single conversation with its contact details and the most recent messages (oldest→newest).
Parameters:
conversationId(required) — string — The conversation id (from list_conversations).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
reply_to_conversationSend 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.
Parameters:
conversationId(required) — string — The conversation id to reply in.content(required) — string — The reply text to send to the visitor.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
resolve_conversationMark a conversation as RESOLVED (closes it). The visitor's widget will no longer show it as active.
Parameters:
conversationId(required) — string — The conversation id to resolve.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
add_knowledgeTrain 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.
Parameters:
type(required) — string — 'url' to crawl a website, or 'qa' to add a question/answer pair.url— string — Website root URL to crawl. Required when type='url'.answer— string — The answer. Required when type='qa'.question— string — The question. Required when type='qa'.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_knowledgeList 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.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
search_knowledgeSemantic 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).
Parameters:
query(required) — string — The search query / user question.topK— integer — Max number of chunks to return (default 5).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
configure_agentConfigure 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.
Parameters:
model— string — Chat model id, e.g. gpt-4o-mini.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.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
set_keywordsAdd 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').
Parameters:
keywords(required) — array — Trigger words/phrases (case-insensitive).reply(required) — string — The reply text to send.matchType— string — CONTAINS (default) = keyword appears anywhere in the message; EXACT = whole message equals the keyword.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
manage_faqList, 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`.
Parameters:
action(required) — string — Which FAQ operation to run.id— string — FAQ item id. Required for 'update' and 'delete'.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'.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_analyticsReturn 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).
Parameters:
days— integer — Look-back window in days for the conversation/message stats (default 30).
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
searchSearch 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.
Parameters:
query(required) — string — The search query or user question.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
fetchFetch 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.
Parameters:
id(required) — string — The document id returned by the search tool.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.