# Sitespeakai — how to use (mcp.ai)

Connect your Sitespeakai account and use 4 tools for AI chatbots straight from your AI agent. Connect with your own API key. SiteSpeakAI enables businesses to automate customer support by creating custom-trained, embeddable GPT chatbots that provide real-time answers about products and services, reducing support tickets.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_sitespeakai?ms=1787291340000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `sitespeakai_get_leads`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/sitespeakai`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/sitespeakai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/sitespeakai/get/leads` — Tool to retrieve all leads for your chatbot. Use when you need to access contact information captured through chatbot interactions.
  - body: { chatbot_id: string }
- `POST https://api.mcp.ai/api/sitespeakai/get/prompts` — Tool to retrieve smart prompts available for a chatbot. Use when you need to list prompts before selecting or managing them.
  - body: { chatbot_id: string }
- `POST https://api.mcp.ai/api/sitespeakai/get/user` — Tool to retrieve details of the authenticated user account. Use after obtaining a valid bearer token and when you need the current user's profile.
- `POST https://api.mcp.ai/api/sitespeakai/list/chatbots` — Tool to list all chatbots. Use when you need an overview of every chatbot linked to your account. No parameters required.

## Example prompts
- "What can I do in Sitespeakai?"
- "Show me a summary of my Sitespeakai account"

## More
- Page: https://mcp.ai/sitespeakai
- Agent spec (llms.txt): https://mcp.ai/sitespeakai/llms.txt
- Postman collection: https://mcp.ai/sitespeakai/postman.json