MCP tools: connect your own MCP servers
MCP tools: connect your own MCP servers
MCP tools let an AI Agent use tools that already live on an MCP server your company runs. Connect the server by URL, and every tool it exposes is discovered. You do not rebuild each one by hand.
Every discovered tool starts off. You turn on the tools the Agent may use, and the Agent calls them during a conversation to fetch or update data in your systems. You connect the server once, then choose per tool who it acts as: a shared connected account for company-wide or public data (works on all channels), or customer sign-in for a person’s own data (Ada web chat, Twilio SMS, Twilio WhatsApp, and Ada Instagram).
To learn more, see MCP tools.
Set how your Voice AI Agent says a Glossary term
Your Voice AI Agent can now say a Glossary term the way you want callers to hear it.
What’s new
A Glossary term can carry a Voice pronunciation for each written form the AI Agent may speak. Use it for brand names, acronyms, and product names that text-to-speech reads the wrong way.
- One row for each written form. Every User term gets a row. On a Custom term, each language’s AI Agent response term gets a row too.
- Spell the term as it sounds. Type
sockso the AI Agent saysSOCas a word, not as three letters. - Hear it before you save. Select the play button to hear the row in the voice configured for that language.
- Leave a row unchanged to store nothing. Each row starts filled with its own term.
- Transcripts keep the term as written. The caller hears the pronunciation. Transcripts and reports still show the term as you wrote it.
This applies to Voice conversations only. Web Chat and Email are not affected.
Learn more about setting how a term is spoken on Voice.