
TL;DR: We've built the Vapi CLI to bring world-class developer experience to your terminal and IDE. Drop Vapi into any project with one command, debug webhooks locally without ngrok, and turn your IDE into a Vapi expert with MCP integration.
Building voice AI agents shouldn't require constantly switching between your terminal, browser, and IDE. You shouldn't need to set up ngrok tunnels just to test webhooks. And your IDE definitely shouldn't hallucinate Vapi APIs that don't exist.
That's why we built the Vapi CLI - a command-line interface designed from the ground up to give developers the best possible experience when building voice AI applications.
The Vapi CLI gives you complete control over your voice AI infrastructure without leaving your terminal:
# List and manage your voice assistants
vapi assistant list
vapi assistant create
# Handle phone numbers and calls
vapi phone list
vapi call create
# Configure webhooks and tools
vapi webhook create https://myapp.com/webhook
vapi tool create
# Debug with real-time logs
vapi logs calls
vapi logs webhooks
Every feature in the Vapi dashboard is now available as a simple command. No more context switching between terminal and browser when you're in the flow.
The magic happens with vapi init. Point it at any codebase and it automatically:
cd my-existing-app
vapi init
# Detected: Next.js application
# ✓ Installed @vapi-ai/web SDK
# ✓ Generated /components/VapiButton.tsx
# ✓ Created /pages/api/vapi/webhook.ts
# ✓ Added environment template (.env.example)
No more copy-pasting from docs or figuring out integration patterns. You get production-ready code that follows best practices for your specific setup.
Here's something that will change how you develop with Vapi: MCP (Model Context Protocol) integration.
Run vapi mcp setup and your IDE's AI assistant (Cursor, Windsurf, VSCode with Copilot) gains complete, accurate knowledge of Vapi's APIs, features, and best practices.
Before MCP:
After MCP:
Ask your IDE: "How do I create a voice assistant that transfers calls to a human?" and get real, working Vapi code instead of guesswork.
Testing webhooks during development has always been painful. Not anymore.
vapi listen --forward-to localhost:3000/webhook
That's it. The CLI starts a local server that receives all your Vapi webhook events and forwards them to your development server in real-time.
What you get:
The CLI isn't just a development tool - it's designed for your entire workflow:
# Multi-account support for teams
vapi auth switch production
vapi auth switch staging
# Comprehensive logging and monitoring
vapi logs errors
vapi logs calls --assistant-id abc123
# Campaign management at scale
vapi campaign create
vapi campaign list
Whether you're prototyping your first voice agent or managing production campaigns with thousands of calls, the CLI scales with your needs.
curl -sSL https://vapi.ai/install.sh | bash
vapi login
vapi init
That's it. You're ready to build voice AI agents with the best developer experience possible.
The Vapi CLI is just the beginning. We're building toward a future where voice AI development is as smooth and intuitive as any other part of your stack.
Stop context switching. Start shipping voice AI agents faster than ever before.
The Vapi CLI is available now. Install it, try it, and let us know what you think. We're just getting started.