Connect Claude, Cursor, or any MCP client to your Slide account with a URL and an API key. Ask it who signed up this week, why an automation did not fire, or to draft a campaign, and it works against your real data. Nothing to install.
The whole setup
https://slide.synquic.com/api/mcp
Authorization: Bearer sk_live_...Sixty-two tools across the platform. Reads are available immediately; anything that sends, spends or deletes waits for you to allow it.
Search the unified contacts hub, read a contact history, and leave notes an agent can pick up later.
Read delivery logs and templates across WhatsApp, email, SMS and RCS. Send through one unified call, with fallback between channels.
List, read and build automation flows, inspect run history step by step, and diagnose why a flow did not fire.
Create and configure AI voice agents, read call records and transcripts, and review call analytics.
Answer order status and delivery questions from connected store data, and check whether a discount code is still valid.
A generic request tool reaches any endpoint the API exposes, so new capabilities are usable the day they ship.
claude mcp add --transport http slide https://slide.synquic.com/api/mcp \
--header "Authorization: Bearer sk_live_..."Sending a message, launching a campaign, placing a call and deleting anything are all withheld until you add the writes header. A read-only connection cannot reach a customer.
Every tool call is made with your own key and passes the same checks a normal request does. An endpoint your scopes do not cover returns 403. Connecting an assistant grants it nothing extra.
An automation built through an assistant is always created paused, whatever it asked for. Going live is a separate, deliberate step a person can review first.
It is an implementation of the Model Context Protocol that exposes Slide to an AI assistant. Once connected, Claude or Cursor can read your contacts, campaigns, message logs and analytics, and, when you allow it, send messages, build automations and manage voice agents.