Connect Claude, Cursor, or any MCP client to the AI Chatbot management MCP server and run your account in plain English. Includes the one-line Claude Code plugin.
AI Chatbot has a management MCP (Model Context Protocol) server that lets an AI agent run your account for you. Connect Claude, Cursor, or any MCP client and ask in plain English: read your analytics, find what is not working, and fix it.
The easiest way in is the Claude Code plugin, which bundles the connection and a skill that knows how to work on a AI Chatbot chatbot. You can also connect any other MCP client directly.
This is the management MCP: it works on your account and chatbots (settings, analytics, sources, inbox). It is different from the MCP Endpoint, which lets AI agents query a single chatbot’s knowledge base.
Once connected, an agent can:
Some things you can ask:
Claude connects with your AI Chatbot login. You do not need an API token.
In Claude, open Settings > Connectors and click Add custom connector. Enter the name AI Chatbot and the URL https://api.sitespeak.ai/mcp, then click Add.
Click Connect. Sign in to AI Chatbot and click Authorize to approve the connection.
Start asking
Claude shows your chatbots, inbox threads and leads in an interactive AI Chatbot app inside the chat. Open it in full view to switch between the inbox, leads, analytics and knowledge sources, read a whole conversation, and reply to a visitor.
Claude asks you to confirm before it changes a setting or sends a reply to a visitor. To remove the connection, open Settings > Connectors in Claude and disconnect AI Chatbot.
Claude Code, Cursor and other MCP clients connect with an API token. Create one on the API tokens page in your account. The agent acts only on the chatbots that token can access.
An API token can read and change your account. Treat it like a password, and only paste it into tools you trust.
The Claude Code plugin bundles the MCP connection and a skill that runs a safe, step-by-step loop: it reads your data, proposes changes, and waits for your confirmation before writing anything.
Add the marketplace
In Claude Code, run:
/plugin marketplace add AI Chatbot/sitespeak-claude-plugin
Install the plugin
/plugin marketplace add AI Chatbot/sitespeak-claude-plugin
Claude Code asks for your API token during install and stores it securely (in the macOS Keychain, or an encrypted credentials file on other platforms). The MCP server connects on its own.
Ask Claude to work on your chatbot, for example: “List my AI Chatbot chatbots” or “Optimize my support bot for lead capture.”
The plugin is open source. See the code on GitHub.
Any MCP client that supports Streamable HTTP with a bearer token can connect to the management MCP directly.
Add this to your claude_desktop_config.json, then restart Claude Desktop:
{
"mcpServers": {
"sitespeak": {
"type": "http",
"url": "https://api.sitespeak.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}
{
"mcpServers": {
"sitespeak": {
"type": "http",
"url": "https://api.sitespeak.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}
Endpoint: https://api.sitespeak.ai/mcp
Header: Authorization: Bearer YOUR_API_TOKEN
{
"mcpServers": {
"sitespeak": {
"type": "http",
"url": "https://api.sitespeak.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_TOKEN"
}
}
}
}
The step-by-step confirmation loop is part of the Claude Code plugin’s skill. Other MCP clients call the tools directly, so review what your client is about to do before you approve a change.
Run /reload-plugins in Claude Code, or restart it, to load the bundled MCP server.
In Claude, disconnect AI Chatbot in Settings > Connectors and connect it again. In other clients, confirm your API token is valid. Create a new one on the API tokens page and reconnect.
Answer rate, sentiment, and question insights come from scheduled jobs, so they lag and are empty for brand-new or low-traffic bots. Empty does not mean there are no gaps.