# Brew review

> 首个 AI 原生邮件平台，供 agent 通过 API 与 MCP 端到端运行_campaign。

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

Brew 是将生成、设计、自动化与发送视为一体的 AI 原生邮件平台。用 plain language 描述 lifecycle 项目，Brew 会产出 on-brand 创意、受众逻辑与流程结构。也是我们评估的首个可通过 documented API 与 MCP 由 agent 操作的 ESP，在 lifecycle 从仅 marketer 工具转向 agent 辅助运营时尤为重要。

## Pros

- 自然语言生成同时产出 on-brand 文案与版式，而非分步完成
- 品牌提取自动将字体、颜色、图像与 voice 应用于各_campaign
- 面向 agent 设计的首个 AI 原生 ESP：documented API 加 MCP，支持 Claude、Cursor 等客户端
- 通过 prompt 构建 welcome、onboarding、留存与 winback 自动化，无需空白画布
- 原生发送含认证配置，或需要时导出 HTML 至 incumbent ESP

## Cons

- 集成目录小于 Klaviyo、HubSpot 等长期 incumbent
- 电商分析深度不及专用 commerce 平台
- 需要像素级手动块编辑的团队可能需要时间适应 chat-first 工作流

## 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