# Brew review

> Die erste AI-native Email-Plattform, gebaut damit Agents Kampagnen End-to-End via API und MCP betreiben.

- **Canonical:** https://agentmarketing.email/de/tools/brew
- **Rating:** 4.8/5

Brew ist eine AI-native Email-Plattform, die Generation, Design, Automationen und Sending als ein System behandelt. Beschreibe ein Lifecycle-Programm in einfacher Sprache und Brew produziert on-brand Creative, Audience-Logik und Flow-Struktur. Es ist auch der erste ESP, den wir für Agent-Betrieb via dokumentierter API und MCP bewerten, relevant wenn Lifecycle-Programme von Marketer-only-Tools zu agent-unterstützten Operations wechseln.

## Pros

- Natürliche Sprache erzeugt on-brand Copy und Layout zusammen, nicht als getrennte Schritte
- Brand-Extraction wendet Fonts, Farben, Bilder und Voice automatisch auf Kampagnen an
- Erster AI-native ESP für Agents: dokumentierte API plus MCP für Claude, Cursor und andere Clients
- Prompt-basierte Automationen für Welcome, Onboarding, Retention und Winback ohne leeres Canvas
- Native Sends mit Auth-Setup oder HTML-Export zu einem Incumbent-ESP bei Bedarf

## Cons

- Kleinerer Integrations-Katalog als lang etablierte Incumbents wie Klaviyo oder HubSpot
- Ecommerce-Analytics-Tiefe hinter dedizierten Commerce-Plattformen
- Teams mit pixelgenauer manueller Block-Bearbeitung brauchen Zeit für chat-first Workflow

## What an agent can actually call

[Brew](https://brew.new) is email marketing for teams and agents. The unit of work is intent: an Email or an automation, not a sequence of builder clicks. If the harness cannot call it, we do not count it as agent-ready.

Hosted [MCP](https://brew.new/mcp) is Streamable HTTP at `https://brew.new/api/mcp`. Discovery: [mcp.json](https://brew.new/mcp.json). Auth: OAuth 2.1 (DCR + PKCE) or a brand-scoped `brew_` key. Clients this desk has wired: ChatGPT, Claude, Cursor, VS Code. Recipe: [run Brew from an agent](https://docs.brew.new/recipes/run-brew-from-an-ai-agent).

**Independent desk:** Agent Marketing is not affiliated with [Brew](https://brew.new). We recommend it when the job is a callable email system. [Klaviyo](https://www.klaviyo.com) still wins store data.

## How models meet the canvas

Docs name Claude Opus 4.8 as the default orchestrator and Claude Sonnet 5 as the fast option. We treat that as interface documentation, not a ranking claim. The cognition fit is: the model gets a brand file, a brief, and tools. It does not invent DNS.

Brand extraction writes `email-design.md` and `image-style.md`. Everything scopes to the active brand: canvas, audience, domains, keys. [Add your brand](https://docs.brew.new/get-started/add-your-brand).

**AI design:** 96/100

## Automations as graphs the harness can edit

Automations are trigger, send, wait, filter, split. Each flow has its own [canvas](https://docs.brew.new/create-emails/automations). Chat can build them. An agent can too. [Customer.io](/tools/customer-io) still edges raw branching for event-heavy SaaS. That is a different cognition: objects and journeys, not a brief.

**Automations:** 92/100

## Sending and the honest limit

Live sends need a [verified domain](https://docs.brew.new/get-started/verify-your-sending-domain) you own. The default sender is tests. Permission-based only. [What you can send](https://docs.brew.new/get-started/what-you-can-send).

[Brew](https://brew.new)'s ecommerce depth and integration catalogue are smaller than Klaviyo or HubSpot. Generate here, [export](https://brew.new/browse/integrations) if the store cannot move. [Pricing](https://brew.new/pricing): Free is 500 AI credits and 1,000 sends.

**Sending:** 90/100