AI features

The Ticket summary feature uses AI to generate a concise summary of a ticket's entire conversation history. Agents can generate a summary directly from the ticket at any time, so they can quickly understand the context without needing to read every individual message. In this article - [How it works](#howItWorks) - [Setting up Ticket summary](#setup) - [Using Ticket summary](#using) - [Generating a summary](#generating) - [Refreshing an outdated summary](#refreshing) How it works When an ag...

LiveAgent exposes a built-in MCP server (Model Context Protocol) that lets you connect external AI tools, such as ChatGPT, Claude Desktop, Cursor, claude.ai, [FlowHunt](https://flowhunt.io), or any other MCP-compatible client, directly with your LiveAgent account. Once connected, your own AI tools/agents can read ticket data and perform actions on your behalf, using your agent identity and permissions. There are two ways to authenticate your MCP client - OAuth 2.1 (recommended), where the AI to...

This article documents the tools exposed by the LiveAgent MCP server, including the exact parameters each tool accepts and the exact fields it returns. A [personal MCP connection](https://support.liveagent.com/647358-MCP-Integration-for-Agents) offers every tool the agent's role has the privileges for, while an [AI agent MCP connection](https://support.liveagent.com/466386-AI-Agents-feature-overview) offers only the tools selected for that AI agent. Every tool returns a single JSON object. A ca...