SiteGPT is listed in Claude's connector directory, at claude.ai/directory/connectors/sitegpt. Anyone can check it: open the directory in Claude, search for SiteGPT, and the Connect button is there. There is no URL to paste and no custom connector form.
This page covers what the listing means, how to add the connector, and what it can and cannot do. For a full setup walkthrough, see the guide to building and running a chatbot from Claude.
iShort answer
Claude users can add SiteGPT from the official connector directory in two clicks: find the listing, then approve access over OAuth in the browser. The connector is SiteGPT's remote MCP server with three tools. search finds the right operation, execute_read reads data, and execute_write changes things after asking. Permissions are a subset of the connecting user's own dashboard role, never more.
Two clicks of setup, then the connector is a control surface for your live chatbot.
Find the listing
In Claude, open the connector directory and search for SiteGPT, or go to claude.ai/directory/connectors/sitegpt and click Connect.
Approve over OAuth
A browser window signs you in to SiteGPT and asks what to grant: all chatbots or only selected ones. No API keys touch the chat.
Ask the first question
Try: "List my chatbots and their status." "Pull yesterday's leads and draft follow-ups." "Which questions did the bot fail to answer this week?"
What does it mean that SiteGPT is in Claude's connector directory?
It means Claude users can find and add SiteGPT from inside Claude without any manual setup. The directory is Claude's catalog of connectors, which are integrations built on MCP, the open Model Context Protocol. MCP is how Claude talks to outside tools.
Before the listing, connecting SiteGPT meant adding https://sitegpt.ai/mcp as a custom connector by hand. The listing removes that step and puts SiteGPT where Claude users already look for tools.
The listing reads SiteGPT, "Manage AI support chatbots from your AI assistant", and carries the directory's Community label. A listing is a distribution fact, not an endorsement, and Anthropic does not certify SiteGPT by listing it. The connector behind it is unchanged: the directory is a shorter path to the same remote MCP server, with the same OAuth approval and permission limits.
How do you add SiteGPT to Claude?
Open the connector directory in Claude, search for SiteGPT, and click Connect. A browser window opens, you sign in to your SiteGPT account, and the approval screen asks whether the grant covers all your chatbots or only selected ones. That completes the setup.
No API key is generated, pasted into a chat, or stored by the client. The server advertises its OAuth metadata automatically, and clients register through Dynamic Client Registration, so there is nothing to configure. Disconnecting the connector in Claude's settings ends its access.
What can the SiteGPT connector do?
It can read your chatbot data and, with your confirmation, change it. The interface is three tools, and they explain every capability and every limit.
| Tool | What it does | What that means in practice |
|---|---|---|
| search | Finds the right operation in the SiteGPT API v2 catalog | Claude discovers what is possible instead of guessing |
| execute_read | Runs read-only calls through an authenticated bridge | List bots, pull conversations and leads, check usage |
| execute_write | Creates, updates, and deletes, marked destructive | Update knowledge, edit personas, always with a confirmation step |
On day one, you ask in plain language:
- "List my chatbots and their status."
- "Pull yesterday's leads, qualify them, and draft follow-up emails."
- "Add the new refund policy page to the bot's knowledge."
- "Which questions did the bot fail to answer this week, and what should the missing help article say?"
The first three are reads and writes against your live workspace. The last one pairs a read with drafting, which assistants do well. More on what this changes for support teams is at MCP for customer service.
What can't the connector do?
It cannot exceed your own permissions. The client never receives permissions or chatbot access your dashboard user does not have. A read-only teammate's Claude cannot edit knowledge, and an approval scoped to one chatbot cannot touch the others.
Anything destructive goes through execute_write. That tool is marked destructive so clients confirm before acting. The connector also does not answer your customers. The widget on your site keeps doing that, and the connector cannot see anything your own login could not.
Being operable by an assistant is also what moves a chatbot toward the agent end of the autonomy scale. AI agent vs chatbot explains where SiteGPT sits on that scale and why consequential actions still route to a human.
What should you do after connecting SiteGPT?
Start by asking it questions. Ten support analytics questions to ask Claude about your chatbot has the exact prompts, from "which questions did the bot fail to answer this week" to a Monday summary written for your Slack channel.
If the directory listing is how you found SiteGPT, the product behind it is a customer service chatbot trained on your own content. Plans start at $39/mo billed yearly on Starter ($59 billed monthly), listed on SiteGPT's pricing. Every plan starts with a 7-day free trial, and the trial requires a credit card.
The same MCP server works from other tools. Claude Code in the terminal, Cursor in the editor, and Codex in CI each have a setup guide. The SiteGPT CLI covers scripted runs and a local MCP server, walked through in the chatbot CLI guide.
For standing agents that hold a role across sessions, see OpenClaw and Hermes. The agents page is the overview of what an assistant can operate end to end, and the AI agents for customer service hub covers the wider category.
Frequently asked questions
What is Claude's connector directory? A catalog inside Claude where users browse and add connectors. Connectors are integrations that let Claude work with outside tools over MCP, the open Model Context Protocol. Instead of pasting a server URL as a custom connector, you find the tool in the directory and click Connect. SiteGPT's listing is at claude.ai/directory/connectors/sitegpt, and the underlying connector is the same remote MCP server documented at sitegpt.ai/mcp-server.
Does being listed mean Anthropic endorses or certifies SiteGPT? No. The listing means the connector is available in Claude's catalog and users can add it without manual setup. It carries no certification or partnership claim. The security facts you can check are OAuth in the browser, no API keys in chat, and permissions scoped to the connecting user's own dashboard role.
What can Claude do with SiteGPT once connected? The connector exposes three tools. search finds the right operation in the SiteGPT API v2 catalog. execute_read runs read-only calls, so Claude can list chatbots, pull conversations and leads, and check usage. execute_write handles creates, updates, and deletes, and it is marked destructive so clients ask for confirmation before changing anything.
What permissions does Claude get over my SiteGPT account? Only yours, at most. The connection is approved over OAuth in the browser, and the client cannot receive permissions or chatbot access your dashboard user does not have. The approval can be scoped to all chatbots or only selected ones, and disconnecting the connector ends its access.
Do I need Claude to use SiteGPT? No. The dashboard, the Agent API v2, and the CLI all operate the same chatbot, and the widget keeps answering visitors on your website either way. The connector adds a control surface for work you would otherwise do by clicking through screens: checking leads, updating knowledge, and reviewing what the bot could not answer.
Does this work with assistants other than Claude? The server is built on the open MCP standard, and Claude is the confirmed client. SiteGPT publishes setup guides for driving it from Claude Code, Cursor, Codex, OpenClaw, and Hermes. An assistant is listed as confirmed only after the connection test passes. The SiteGPT ChatGPT app has not been approved, so it is not available.
Sources
- SiteGPT MCP server page for the directory listing statement, the three tools and their descriptions, the server URL, Dynamic Client Registration, and the subset permission wording, read 14 August 2026
- Claude connector directory listing for the listing name, description, and Community label, verified from a signed-in Claude session on 14 August 2026
- Model Context Protocol for the open standard the connector is built on
- SiteGPT pricing for plan rates and the 7-day trial