MCP App Store
by KeenEthics
SiteGPT icon

SiteGPT MCP Server for Claude and ChatGPT

By SiteGPT

Overview

SiteGPT builds AI customer-support chatbots trained on your website. This connector links your AI assistant to your SiteGPT account over MCP with browser OAuth — no API keys. Three compact tools cover the whole platform: search finds the right operation in the API catalog, execute_read fetches data (chatbots, conversations, leads, analytics), and execute_write makes changes (create chatbots, add knowledge, update prompts and settings) — reads run without interruption, writes always confirm first. Everything is bounded by the OAuth grant you approve: your role, your token scopes, your chatbot restrictions.

How to connect

  1. Claude: Open the SiteGPT listing in the Claude connectors directory and choose Connect. Claude listing SiteGPT exposes 3 tools here.
  2. ChatGPT: Open the SiteGPT listing in the ChatGPT app directory and choose Connect. ChatGPT listing SiteGPT exposes 21 tools here.

Tools

authorize_knowledge_source

ChatGPT
Get a fresh browser authorization URL for an existing knowledge source connection (for example one still pending OAuth) at its third-party provider (Notion, Google Drive, Confluence, and others). Uses POST /api/v2/chatbots/{chatbotId}/knowledge/sources/{connectionId}/authorize.

create_knowledge_source

ChatGPT
Create a new OAuth knowledge source connection (Notion, Google Drive, Dropbox, OneDrive, Box, SharePoint, or Confluence) and get the browser authorization URL to finish connecting it. Confluence additionally requires the site domain (e.g. your-team.atlassian.net). GitHub is not available here — its connections carry an access token and must be set up in the SiteGPT dashboard. Once authorized, the connection pulls content from that third-party provider. Uses POST /api/v2/chatbots/{chatbotId}/knowledge/sources.

execute_read

ChatGPT
Run read-only SiteGPT API v2 calls (GET only) using JavaScript code. Targets the SiteGPT API v2 (spec: https://sitegpt.ai/api/v2/openapi.json, docs: https://sitegpt.ai/docs/api-reference/v2/getting-started). First use 'search' to find the right endpoints. Requests run through an authenticated host-side bridge scoped to your OAuth grant. Write methods (POST, PUT, PATCH, DELETE) are rejected here — use the execute_write tool for those. Available in your code: interface RequestOptions { method: "GET"; path: string; query?: Record<string, string | number | boolean | undefined>; body?: unknown; contentType?: string; rawBody?: boolean; } // OpenAPI 3.x spec with $refs resolved inline. // The spec object follows the standard OpenAPI 3.x structure. interface OperationObject { summary?: string; description?: string; operationId?: string; tags?: string[]; parameters?: Array<{ name: string; in: "query" | "header" | "path" | "cookie"; required?: boolean; schema?: unknown; description?: string; }>; requestBody?: { required?: boolean; description?: string; content?: Record<string, { schema?: unknown }>; }; responses?: Record<string, { description?: string; content?: Record<string, { schema?: unknown }>; }>; security?: Array<Record<string, string[]>>; deprecated?: boolean; } interface PathItem { summary?: string; description?: string; get?: OperationObject; post?: OperationObject; put?: OperationObject; patch?: OperationObject; delete?: OperationObject; head?: OperationObject; options?: OperationObject; trace?: OperationObject; parameters?: OperationObject["parameters"]; } interface OpenApiSpec { openapi: string; info: { title: string; version: string; description?: string }; paths: Record<string, PathItem>; servers?: Array<{ url: string; description?: string }>; components?: Record<string, unknown>; tags?: Array<{ name: string; description?: string }>; } declare const codemode: { spec(): Promise<OpenApiSpec>; request(options: RequestOptions): Promise<unknown>; }; Your code must be an async arrow function that returns the result. Example: async () => { return await codemode.request({ method: "GET", path: "/your/endpoint" }); } SiteGPT API v2 is scoped by the bearer token used for this MCP connection. Use search first, then execute_read for lookups and execute_write for changes — /api/v2 paths only.

execute_write

ChatGPT
Create, update or delete SiteGPT API v2 resources (POST, PUT, PATCH or DELETE only) using JavaScript code. Targets the SiteGPT API v2 (spec: https://sitegpt.ai/api/v2/openapi.json, docs: https://sitegpt.ai/docs/api-reference/v2/getting-started). First use 'search' to find the right endpoints and 'execute_read' for any lookups. Requests run through an authenticated host-side bridge scoped to your OAuth grant. GET is rejected here — use the execute_read tool to read data. GitHub knowledge-source connections cannot be created or updated through this tool because they carry an access token — direct users to the SiteGPT dashboard for GitHub setup; OAuth-based connectors (Notion, Google Drive, …) can be created here and finish authorization in the browser. Available in your code: interface RequestOptions { method: "POST" | "PUT" | "PATCH" | "DELETE"; path: string; query?: Record<string, string | number | boolean | undefined>; body?: unknown; contentType?: string; rawBody?: boolean; } // OpenAPI 3.x spec with $refs resolved inline. // The spec object follows the standard OpenAPI 3.x structure. interface OperationObject { summary?: string; description?: string; operationId?: string; tags?: string[]; parameters?: Array<{ name: string; in: "query" | "header" | "path" | "cookie"; required?: boolean; schema?: unknown; description?: string; }>; requestBody?: { required?: boolean; description?: string; content?: Record<string, { schema?: unknown }>; }; responses?: Record<string, { description?: string; content?: Record<string, { schema?: unknown }>; }>; security?: Array<Record<string, string[]>>; deprecated?: boolean; } interface PathItem { summary?: string; description?: string; get?: OperationObject; post?: OperationObject; put?: OperationObject; patch?: OperationObject; delete?: OperationObject; head?: OperationObject; options?: OperationObject; trace?: OperationObject; parameters?: OperationObject["parameters"]; } interface OpenApiSpec { openapi: string; info: { title: string; version: string; description?: string }; paths: Record<string, PathItem>; servers?: Array<{ url: string; description?: string }>; components?: Record<string, unknown>; tags?: Array<{ name: string; description?: string }>; } declare const codemode: { spec(): Promise<OpenApiSpec>; request(options: RequestOptions): Promise<unknown>; }; Your code must be an async arrow function that returns the result. Example: async () => { return await codemode.request({ method: "POST", path: "/your/endpoint", body: { name: "..." } }); } SiteGPT API v2 is scoped by the bearer token used for this MCP connection. Use search first, then execute_read for lookups and execute_write for changes — /api/v2 paths only.

get_chatbot_analytics

ChatGPT
Get chatbot analytics for the inline analytics card: message counts and feedback split, training/knowledge state (from the chatbot dashboard endpoint), account-wide quota usage with a 12-month message-volume history (from the usage endpoint), and trailing-30-day engagement totals — widget opens, conversations started, unique visitors, escalations, leads (from the analytics endpoint; null when the account does not have analytics enabled). Uses GET /api/v2/chatbots/{chatbotId}/dashboard, GET /api/v2/usage, and GET /api/v2/chatbots/{chatbotId}/analytics.

get_chatbot_appearance

ChatGPT
Read the chatbot widget appearance (colors, launcher position and shape, title, welcome message, placeholder, tooltip) plus its starter questions, for the inline appearance card. Uses GET /api/v2/chatbots/{chatbotId}/settings/appearance and GET /api/v2/chatbots/{chatbotId}/starters.

get_conversation

ChatGPT
Read one conversation with its transcript (visitor questions and chatbot/system answers, capped at 2000 characters per message). Renders as the transcript panel of the inline conversations inbox. Uses GET /api/v2/chatbots/{chatbotId}/conversations/{threadId}.

list_conversations

ChatGPT
List a chatbot conversation inbox with filters (open/resolved status, escalated-only) and cursor pagination, projected to compact rows with a last-message snippet. Renders as the inline conversations inbox. Uses GET /api/v2/chatbots/{chatbotId}/conversations.

list_escalations

ChatGPT
List the open conversations that are escalated to a human and waiting — the queue behind the inline escalations view — with cursor pagination for queues longer than one page. Read-only: to reply to a visitor, use reply_to_conversation. Uses GET /api/v2/chatbots/{chatbotId}/conversations with escalated=true and status=open.

list_knowledge_sources

ChatGPT
List a chatbot connector data sources (Notion, Google Drive, Confluence, …) with their sync state, plus document counts by ingestion status. Renders as the inline knowledge view. Uses GET /api/v2/chatbots/{chatbotId}/knowledge/sources and GET /api/v2/chatbots/{chatbotId}/documents/stats.

list_leads

ChatGPT
List the leads a chatbot collected (name, email, phone, received time, starred/archived flags) with search, status filter, and cursor pagination. Renders as the inline leads browser. Uses GET /api/v2/chatbots/{chatbotId}/leads.

open_sitegpt

ChatGPT
Open the SiteGPT home: switch between your chatbots and work with conversations, escalations, leads, analytics, and knowledge sources in one place. Takes no arguments. Opens from the ChatGPT sidebar or on request. Uses GET /api/v2/chatbots (every page, up to 1,000 chatbots).

open_sitegpt_inbox

ChatGPT
Open the SiteGPT support inbox as a panel in this conversation: switch between your chatbots and browse conversations, escalations, and leads. The conversation or lead you open becomes context for this chat, so you can ask for a summary or a draft reply. Takes no arguments. Uses GET /api/v2/chatbots.

preview_chatbot

ChatGPT
Render a live, interactive preview of a SiteGPT chatbot directly in the conversation (MCP Apps extension). Call it after creating or inspecting a chatbot, passing the chatbot id — an RFC-4122 UUID or a 15-20 digit numeric id — and optionally the chatbot title for the preview header. Returns { chatbotId, widgetUrl }; hosts that support MCP Apps render the actual chat widget from the ui://sitegpt/chatbot-preview resource, and any client can open widgetUrl in a browser instead. Performs no API calls and does not verify that the chatbot exists — use execute_read for lookups. Note: chatbots that restrict embedding via Allowed Domains (Settings > General) block the inline frame; the preview then switches to a built-in chat driven by the send_chat_message tool, and shows a fallback with the direct link when that fails too.

read_sitegpt_settings

ChatGPT
Read the SiteGPT settings shown on the ChatGPT plugin settings page: for each chatbot (up to 10), lead email notifications, human handoff, how new conversations start (AI, AGENT, or WORKING_HOURS when the chatbot follows its working hours), and whether answers hide sources. Takes no arguments. Uses GET /api/v2/chatbots and GET /api/v2/chatbots/{chatbotId}/settings.

reply_to_conversation

ChatGPT
Send a reply to the visitor of one conversation, as a human agent of the team. The visitor sees it in the chat widget, or on WhatsApp for a WhatsApp conversation. If the team does not handle the conversation yet, the reply takes it over first: the chatbot stops answering it, and the visitor sees that a human agent joined. Send only text that the user wrote or approved. A resolved conversation refuses replies, and so does a conversation on Slack, Crisp, Messenger, or another channel with its own agent inbox (reply there). Renders the conversation with the new reply. Uses POST /api/v2/chatbots/{chatbotId}/conversations/{threadId}/replies.

send_chat_message

ChatGPT
Send a visitor message to a SiteGPT chatbot and get its answer — the data lane behind the inline chatbot preview's built-in chat. The first call (no threadId) creates a conversation and returns its threadId; pass that threadId on follow-ups to continue the same conversation. Messages are capped at 20000 characters (the endpoint's limit). On chatbots in human-support mode the message is delivered but answer is null — a human replies in the site widget. Uses POST /api/v2/chatbots/{chatbotId}/messages and POST /api/v2/chatbots/{chatbotId}/conversations/{threadId}/messages.

update_chatbot_appearance

ChatGPT
Update the chatbot widget appearance: title, welcome message, placeholder, tooltip, brand/launcher/link colors (#rrggbb), and launcher position. Only the provided fields change; the tool returns the full updated appearance. This changes the LIVE widget customers see. Uses PATCH /api/v2/chatbots/{chatbotId}/settings/appearance.

update_sitegpt_settings

ChatGPT
Change SiteGPT settings from the ChatGPT plugin settings page. set maps property names from read_sitegpt_settings (for example leadEmails__<chatbotId>) to new values. Every value is validated before anything is saved. Changes take effect at once on the live chatbot widget and on lead email delivery. Returns every value after the save. Uses PATCH /api/v2/chatbots/{chatbotId}/settings/{section}.

upload_knowledge_file

ChatGPT
Upload one file (base64-encoded, max 1500000 bytes decoded — about 1.5 MB; the MCP transport caps request bodies, larger files go through the dashboard) as chatbot training knowledge. Ingestion is queued asynchronously; once trained, the content shapes the answers the live chatbot gives visitors. Uses POST /api/v2/chatbots/{chatbotId}/knowledge/files.

execute_read

Claude

execute_write

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/sitegpt"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/sitegpt)