--- title: "MCP Server | WhisperChat Connect to Claude, ChatGPT, Cursor & More" description: "Connect WhisperChat to Claude, ChatGPT, Cursor, VS Code, Grok and any MCP client. Build, train and query your AI chatbots straight from your assistant step-by-step setup for every platform." canonical: "https://www.whisperchat.ai/docs/mcp" last-updated: "2026-10-30" source: "https://www.whisperchat.ai/docs/mcp" --- # MCP Server | WhisperChat Connect to Claude, ChatGPT, Cursor & More > Connect WhisperChat to Claude, ChatGPT, Cursor, VS Code, Grok and any MCP client. Build, train and query your AI chatbots straight from your assistant step-by-step setup for every platform. Paid plans only ## Your chatbots, inside your assistant WhisperChat runs a [Model Context Protocol](https://modelcontextprotocol.io/) server. Connect it once and your AI assistant can create chatbots, import your website, train them and test their answers by just asking. No API keys to manage: you sign in with WhisperChat and approve the connection. Paid plan required The MCP server is available on paid subscriptions only. Free accounts can't authorize a connection or create chatbots through it — approving the connection prompts you to upgrade if your plan isn't active. Your plan's normal message and character limits still apply. [View plans](https://www.whisperchat.ai/pricing) See it in action Your browser does not support the video tag. 0:00 / 0:00 Watch an assistant create a chatbot, crawl a site and train it end to end, just by asking. [Add to Claude](https://www.whisperchat.ai/mcp/connect)[Other platforms](https://www.whisperchat.ai/docs/mcp#platforms) Using a coding agent? Paste this in Prompt for Claude Code ``` Install the WhisperChat MCP server for me globally. Run this command: claude mcp add --transport http --scope user whisperchat https://www.whisperchat.ai/mcp Then give me step-by-step instructions to: 1. Restart Claude Code (exit with /exit, then run `claude` again). 2. Run /mcp, pick whisperchat and choose Authenticate to sign in to WhisperChat. 3. Prompt with "WhisperChat onboard me", which should call whisperchat_onboarding and walk me through creating, crawling, training and testing my first chatbot. ``` ## Setup by platform Every client below speaks remote MCP over HTTP. Pick yours for exact steps. ### Claude Claude web and desktop, via custom connectors. [Add to Claude](https://www.whisperchat.ai/mcp/connect) Before you start - Available on Pro, Max, Team and Enterprise. - On Team and Enterprise, an owner or admin has to add the connector for the organisation first. 1. 1 Use the Add to Claude button above it opens Claude's add-connector dialog with the WhisperChat URL already filled in. To do it by hand instead, follow the steps below. 2. 2 Open Claude's connector settings. [claude.ai/customize/connectors](https://claude.ai/customize/connectors) 3. 3 Click the + button, then choose Add custom connector. 4. 4 Name it WhisperChat and paste the server URL. Leave the Advanced OAuth fields empty the server registers your client automatically. Server URL ``` https://www.whisperchat.ai/mcp ``` 5. 5 Click Add, then Connect. Claude sends you to WhisperChat to sign in and approve the permissions, then returns you with the tools ready. Custom connectors are in beta. Claude reviews a connector before it can be used, so a prefilled link never skips that step. Claude connects from Anthropic's servers rather than from your computer, so this works with the hosted WhisperChat server and not with a local dev URL. ## What your assistant can do Once connected, these tools are available. Your assistant picks the right one you just describe what you want. `whisperchat_onboarding`read Start here: a guided walkthrough from first chatbot to embed code. `list_chatbots`read List every chatbot on your account, with its ID. `get_chatbot`read Read one chatbot's full settings. `create_chatbot`write Create a new chatbot. `update_chatbot`write Rename a bot, switch its model, or restyle the whole widget. `delete_chatbot`delete Permanently delete a chatbot. `add_knowledge_source`knowledge Add one page, text snippet or Q&A pair. `crawl_website`knowledge Crawl an entire site into a bot's sources. `train_chatbot`write Train on the current sources. Runs in the background. `get_chatbot_status`read Check training progress for each source. `query_chatbot`read Ask a chatbot a question and get its real answer. `get_embed_code`read Get the snippet to embed the widget on your site. `search`read Search across your chatbots' knowledge sources. `fetch`read Read one knowledge source in full, by ID. Try asking: “Create a chatbot called Support Bot, crawl example.com into it, train it, then ask it what our refund policy is.” Your assistant will chain `create_chatbot` → `crawl_website` → `train_chatbot` → `query_chatbot` on its own. ## Sign-in and permissions WhisperChat's MCP server uses OAuth 2.1 with PKCE. There is no API key to copy, paste or leak your client is sent to WhisperChat to sign in, and you approve exactly what it may do. ### How connecting works 1. 1Your client discovers the server and registers itself automatically. 2. 2It opens WhisperChat in your browser, where you sign in as normal. 3. 3You review the permissions requested and approve the connection. A paid plan is required at this step free accounts are asked to upgrade before a connection is granted. 4. 4The client receives an access token valid for one hour, refreshed silently for 30 days. ### Permissions you grant `chatbot:read` List your chatbots, read their settings and ask them questions. `chatbot:write` Create chatbots, change their settings and start training. `chatbot:delete` Delete chatbots. Granted separately so a mistake can't remove your work. `knowledge:write` Add web pages, text and Q&A pairs to a chatbot's knowledge. A connected client can only ever see chatbots on your own account. Revoke access at any time from your client's connector settings. [REST API docs](https://www.whisperchat.ai/docs/api)[Setup guide](https://www.whisperchat.ai/guide)