Skip to main content
SmartAlex is built for AI-native builders, and it is first-class with Claude Code. Point Claude Code at the live SmartAlex MCP server and you can build and operate a complete voice platform without leaving your agent: spin up a voice agent for a clinic from a single URL, launch an outbound campaign, read call transcripts, and update a deals pipeline, all in one conversation. Most voice tools give an AI agent docs to read. SmartAlex gives it a set of tools to act with. That is why building a voice agent from the terminal actually works here: every capability is exposed as an MCP tool that runs with your permissions, so Claude Code can plan a step, call the right tool, and show you the result.
Honest framing: SmartAlex is agent-native by design and works exceptionally well with Claude Code (our MCP server is live and listed in the Claude MCP directory). It works equally well with other MCP clients like Cursor, VS Code, Windsurf, ChatGPT, and Gemini CLI. This is not an exclusive or official partnership with Anthropic. Claude Code is simply the smoothest way in.

Why it fits Claude Code so well

Claude Code is at its best when it can act safely and reversibly. SmartAlex is designed for exactly that:
  • Every tool is labelled. The server has 80 tools: 31 only read, 30 create or change data, and 19 ask you first because they spend money, contact real people or delete something for good. Every tool carries MCP annotations (readOnlyHint, destructiveHint, idempotentHint), so Claude Code knows a call is a safe read, a retryable update, or a permanent delete before it runs it.
  • Risky actions wait for your yes. Before one of the 19 ask-first actions runs, the server returns a preview of exactly what will happen, with the cost where there is one. Claude Code must show it to you and wait for your yes. Only then can it run the action, with a one-time code from that preview that works once and expires after 10 minutes.
  • Strict per-workspace isolation. Claude Code acts as you, in the workspace you last opened in SmartAlex, with your role’s permissions. An agent connected to your workspace can only ever see and touch your workspace, never another tenant’s data.
The result: you can let Claude Code drive real operations on a live voice platform and still keep tight, predictable boundaries.

Connect Claude Code to SmartAlex

The fastest path is the hosted cloud endpoint over OAuth: no install, no key to copy, no config file.
1

Add the server

Run the command above. Claude Code registers the SmartAlex MCP server and asks you to sign in. If it does not, run /mcp, choose smartalex, then Authenticate.
2

Sign in and allow

Your browser opens. Sign in to SmartAlex and press Allow. Claude Code works in the workspace you last opened in SmartAlex. Nothing to paste back.
3

Ask it to do something

Type a plain request, for example “show me my SmartAlex contacts”. Claude Code selects the right tool and runs it against your workspace.
No API key needed. You connect by signing in. API keys are not self-serve. To see what Claude Code can and cannot do in your workspace, or to disconnect it, read Security and permissions.

What your agent can operate

Once connected, Claude Code can run the platform through conversation. The main areas the tools (all prefixed smartalex_) cover: Tools your plan, add-ons or role don’t allow are hidden. Campaign tools and buying numbers need the Outbound Campaigns add-on. HTTP tools and creating or deleting webhooks need Power Tools. Creating an agent needs a free agent slot. The headline capability: smartalex_create_agent takes a website URL, reads the business, generates an optimized prompt, and deploys a live voice agent in about 30 to 60 seconds. Underneath, SmartAlex runs a curated, high-accuracy speech, language, and voice stack, kept abstracted, so there is nothing for you to tune.

Example prompts

Real requests you can paste into Claude Code once it is connected:
Deleting something for good is an ask-first action, so a request like “delete the old test agent” shows you a preview and waits for your yes before anything is deleted.

A full build, in one conversation

The point of building a voice agent from the terminal is that you never context-switch. A single Claude Code thread can carry a business from URL to live, calling agent: You stay in the loop for anything that spends money, contacts people or deletes for good, Claude Code does the mechanical work, and every action is scoped to your workspace.

Embed the result on your site

When the agent is ready, ask Claude Code for the widget code (smartalex_get_widget_install_code) and drop it in. For a static site, paste this single tag just before the closing body tag:
For a React or Next.js app, inject it from your root layout:
The widget reads its published config (variant, colors, agent) at load time, so you can restyle it in Widget Studio later without touching the site again. This is the same pattern you use for a Lovable, v0, or Bolt export: static HTML gets the script tag, React output gets the useEffect injection.

Live today, coming soon

Live now

The MCP server (cloud and local) and Custom HTTP Tools are in production. These are the programmatic surfaces you build against today.

Coming soon

A public REST API and TypeScript SDK are in private beta. If a shipped REST API is a hard requirement right now, factor that into your timing.

MCP getting started

Connect Claude Code, Cursor, VS Code, ChatGPT, or Gemini CLI in under two minutes.

What an AI agent can do

The 80 tools, what asks you first, and the isolation model.

Build with Cursor, v0, and Bolt

The same MCP server, from other AI-native builder tools.

Pricing and add-ons

Plans, included minutes, and add-ons.