AI & MCP

LLM-powered steps inside your flows, the guardrails that check what passes through them, and the MCP servers that expose a chosen slice of your Tools and APIs to external AI clients.

The end users who sign in to your MCP servers, and their groups and roles, are managed under Account & admin.

Resource	What it covers
AI Agents	LLM-powered flow steps that classify, extract, validate, or generate data.
Guardrails	Safety checks that flag, reject, or mask records that violate policy.
MCP Servers	Your own MCP endpoints exposing a chosen slice of Tools and APIs.
MCP OAuth Providers	OAuth registrations that let external MCP clients authenticate.