Giving voice agents tools with MCP
Your booking system, your CRM, your order lookup — any API can become a voice agent’s tool without writing a line of agent code.
A voice agent that can only talk is a fancy IVR. The useful ones do things: book the slot, look up the order, open the ticket.
MCP is the standard way
The Model Context Protocol turns an API into a set of tools a model can call. Add an MCP server to the catalog, attach it to an agent, and its tools are available on the next call.
Built-in tools for the phone
Some tools only make sense on a call: blind and attended transfers, hold, pausing the recording while a card number is read, and collecting keypad digits. Those are built in.
And the other direction
DialPress is an MCP server itself. An AI assistant with a scoped token can list calls, read call records, or originate a call — nothing more than its scopes allow.
Field notes
Keep reading
Build an AI voice bot like an Express app
The dialpress Node SDK turns SIP into routes and handlers. Here is a PBX and an AI voice bot that share one gateway — and pass calls between them.
SIP vs WebRTC for AI voice agents
SIP reaches every phone number on earth; WebRTC reaches every browser. A production voice agent needs both — here is how they fit together.
Why voice AI needs its own stack
A voice agent is only as good as the call it rides on. Why we built the SIP server, media path, speech, and agent runtime as one stack.