You can build a chatbot trained on your own content and run it from Claude, without opening a dashboard. SiteGPT exposes a remote MCP server that MCP-compatible AI assistants connect to over OAuth. Add one connector URL (https://sitegpt.ai/mcp), approve access in your browser, and Claude can list your bots, pull leads, and update knowledge for you.
iShort answer
SiteGPT trains a customer service chatbot on your content (websites, docs, YouTube, help centers) and keeps it synced. Because the platform speaks MCP, the standard Claude already uses for connectors, managing that bot becomes a conversation: "pull yesterday's leads", "add the new refund policy", "make the persona more concise". Setup takes minutes. Claude is the confirmed client today; ChatGPT (Developer Mode) and Perplexity (Pro+) support remote MCP connectors as of 2026, so this is the standard, not a one-off integration.
Four steps from connector URL to managing a live chatbot in plain language.
Build the bot in SiteGPT
Train it on your website, files, YouTube, help center, and 12+ other sources. Auto-sync keeps it fresh.
Add the connector in Claude
Paste https://sitegpt.ai/mcp as a custom connector. Nothing to install or host.
Approve in the browser
Sign in to SiteGPT over OAuth. No API keys are pasted into a chat.
Run it by asking
List bots, review leads, update knowledge, and edit personas from the conversation.
What changes when your chatbot speaks MCP
Your chatbot's day job does not change: it answers customers on your website from your own content. What changes is how you operate it. Without MCP, every check-in, knowledge update, or lead review means logging into a dashboard and clicking through screens. With MCP, those same operations become one request to the assistant you already have open.
Same chatbot, same data. The difference is how much of your day the routine work takes.
Without MCP
- Log into the dashboard every time you want to check bots, leads, or conversations
- Click through screens to update knowledge, then repeat for every content change
- Export leads to a CSV, then reformat them by hand for your CRM or team
- Persona and settings edits live in forms, separate from where you think and write
- Every task is a context switch away from the work you were doing
With MCP
- Ask Claude "list my chatbots" and get status without leaving the conversation
- Say "add the new refund policy page to the bot" and the knowledge updates
- Say "pull yesterday's qualified leads" and have them summarized, qualified, and drafted into follow-ups in the same chat
- Edit the persona in plain language: "be more concise, stop offering discounts"
- One OAuth approval once; after that, operating the bot is just asking
This is what "MCP chatbot" means in practice: not a different kind of bot, but a chatbot platform that exposes its operations as tools your assistant can call. SiteGPT sits on the server side of the protocol, so there is nothing for you to host or maintain. If you have ever considered a custom MCP chatbot build (your own server, OAuth, tool schemas), this is that outcome as a managed product.
Connect Claude to SiteGPT in four steps
The whole setup takes a few minutes. The detailed walkthrough with screenshots is in how to build and manage a chatbot from Claude; here is the shape of it:
- Build the bot in SiteGPT. Point it at your content: websites, sitemaps, files, YouTube, GitHub, cloud storage, and help centers (12+ sources). Auto-sync keeps trained content current, so answers do not go stale.
- Add the connector in Claude. In Claude's connector settings, add https://sitegpt.ai/mcp as a custom connector. It is a remote MCP server, so there is nothing to install or run locally.
- Approve over OAuth. Claude opens a browser window where you sign in to SiteGPT and approve the connection. No API keys ever touch the chat, and you can revoke access at any time.
- Ask for something. Claude discovers SiteGPT's tools (bots, leads, knowledge, personas) automatically and calls the right one when you ask in plain language. There are no commands to memorize.
One detail worth knowing: the connection is role-aware. The assistant inherits the connecting user's dashboard permissions, nothing more. If a read-only teammate connects Claude, their Claude cannot edit knowledge or personas.
What you can run from Claude today
Operate SiteGPT from Claude today: list bots, review leads, update knowledge, edit personas. These run against your live workspace, in your own words:
- "List my chatbots." Every bot in the workspace with its status, without opening the dashboard.
- "Pull yesterday's qualified leads from the website bot." Claude fetches the lead captures and can summarize, qualify, or format them for a CRM handoff in the same conversation.
- "Add our new refund policy page to the bot's knowledge." The bot picks up fresh content without a retraining project.
- "Make the persona more concise and stop offering discounts." Persona instructions update directly from chat.
The compounding value is in the follow-ups. "Pull yesterday's leads" can become "now draft a follow-up email for the two enterprise ones" without switching tools, because the operations run inside an assistant that can also think and write.
Not just Claude: the rest of the MCP ecosystem
Claude is the confirmed client today: the connection to https://sitegpt.ai/mcp is tested end to end. But the connector is built on the open MCP standard, so any assistant that supports remote connectors can connect. ChatGPT (Developer Mode) and Perplexity (Pro+) support remote MCP connectors as of 2026.
That framing matters when you pick a platform. An MCP chatbot platform is not betting on one vendor's plugin program; it is adopting the same standard the assistant ecosystem is converging on. SiteGPT lists an assistant as confirmed once its connection test passes, so the MCP server docs are the up-to-date source. For the broader shift this fits into, see the guide to AI agents for customer service.
Prefer code? Agent API v2 and the CLI
MCP is the conversational control surface. The same operations are available programmatically, and all three surfaces drive the same underlying chatbot:
| Surface | Best for | Where to start |
|---|---|---|
| MCP server | Operating the bot from Claude in plain language | MCP server docs |
| Agent API v2 | Pipelines and product integrations: create bots, sync knowledge, fetch leads from code | API v2 getting started |
| CLI | Terminal and CI workflows, scripted knowledge updates | CLI onboarding |
A practical split: wire recurring jobs (nightly knowledge syncs, lead exports) to the Agent API v2 or the CLI, and keep the MCP connection for everything ad hoc. API access is included on Growth ($79/mo) and above.
Security and permissions
Connecting an assistant to production customer data deserves scrutiny, so the access model is deliberately narrow:
- OAuth, not shared secrets. Authorization happens in the browser against your SiteGPT account. Nothing sensitive transits the chat, and disconnecting the connector ends the assistant's access.
- Least-privilege, role-aware scopes. The assistant inherits the connecting user's dashboard permissions, nothing more. It can never do something the person who connected it could not do themselves.
- Per-user grants. Each teammate authorizes their own connection under their own role, so access is auditable to a person rather than to a shared workspace key.
SiteGPT's broader security practices, including SOC 2 Type II, are documented at sitegpt.ai/security.
Frequently asked questions
Can Claude really manage a production chatbot? Yes. Once Claude is connected to https://sitegpt.ai/mcp over OAuth, it can list your bots, pull leads, update knowledge, and edit personas against your live workspace. The chatbot keeps answering customers on your website as usual; Claude becomes the control panel.
Which assistants support the SiteGPT MCP server? Claude is the confirmed client today: the connection is tested and documented. ChatGPT (Developer Mode) and Perplexity (Pro+) support remote MCP connectors as of 2026, and SiteGPT is built on the open MCP standard, so any assistant that supports remote connectors can connect. An assistant is listed as confirmed only after the connection test passes.
What is an MCP chatbot? An MCP chatbot is a chatbot you can operate through the Model Context Protocol, the open standard that lets AI assistants call external tools. The bot answers your customers on your website, and you manage bots, leads, knowledge, and personas by talking to an assistant instead of clicking through a dashboard.
What is the difference between an MCP server chatbot and an MCP client chatbot? An MCP server chatbot platform exposes its capabilities as tools that outside assistants call; SiteGPT works this way. An MCP client chatbot connects outward to other MCP servers to fetch data. The terms describe which side of the protocol the chatbot sits on.
Do I need to build a custom MCP server for my chatbot? No. A custom MCP chatbot build means hosting a server, implementing OAuth, defining tool schemas, and maintaining all of it as the spec evolves. SiteGPT ships that as a managed product: a hosted remote MCP server with browser OAuth and role-scoped permissions.
What permissions does Claude get over MCP? The assistant inherits the connecting user's dashboard permissions, nothing more. Scopes are least-privilege and role-aware, and disconnecting the connector ends access.
Is connecting Claude to my chatbot platform secure? Authorization runs over OAuth in the browser, so no API keys are pasted into a chat. Access is scoped to the connecting user's role and revocable at any time. Security practices, including SOC 2 Type II, are on the security page.
How much does this cost? SiteGPT starts at $39/mo (Starter), with Growth at $79/mo and Scale at $259/mo; annual billing saves 40%, and every plan starts with a 7-day free trial. Growth and above include API access alongside the MCP server. Full details are on the pricing page.
Can I still use the dashboard? Yes. MCP is an additional control surface, not a replacement. The dashboard, the Agent API v2, the CLI, and the MCP server all operate the same chatbot.
Last updated: July 2026.