Skip to main content
Brew ships an MCP server with tools for design generation, editing, audiences, sends, automations, and analytics. Connect it to the AI client you already work in. Your email ops become part of the same chat where you plan them. This recipe walks through one session: draft a newsletter, request checks, review a test, and approve a send. Open Brew or your inbox when a step calls for it. The tool catalog lists everything else the server can do.
Before you start. You need a Brew account and an AI client that supports plugins or remote MCP connections. ChatGPT, Claude, Grok, Cursor, Codex, VS Code, and most agent tools do. A verified sending domain is also required if you plan to send for real.

1. Connect Your Client

Use the setup guide for your client, then complete its read-only brand check: Connect Your MCP Client covers ChatGPT web and other clients. MCP Authentication and Scoping explains brand access and revocation. For a new brand, follow Configure a Brand and Domain before starting this recipe.

Approval and Retry Instructions

Give your agent these working instructions after setup:
These instructions set your workflow preferences; they don’t reduce the connection’s permissions. Brew’s own confirmation gate doesn’t apply to a test sent to the connected person. Confirmation has the server’s rules. The retry lines cover every send, test sends included, plus fail-closed checks like audits and inbox placement tests. Safe Retries has the full contract. For marketing consent, see What You Can Send with Brew.

2. Draft the Email

Generation uses Brew credits. After your brand is ready, replace the brackets and request one draft:
If the design is still generating, the agent checks the same draft until it’s ready. Asking for a new draft instead starts another billed design. Open the preview and the Brew link. Check the facts, branding, images, and destination links. If your client doesn’t display a preview, inspect the design in Brew before approving further work.

3. Iterate in the Same Chat

Identify the existing design by its Brew link or email ID:
Content edits create a version and use credits. If the edit is still running, the agent checks back on it until it finishes. You can restore an earlier version if needed. A rename, inbox subject change, language change, or folder move alone is free and creates no version.

4. QA with Agent Tools

The full pre-send routine runs from the same chat:
“Preview this across Gmail, Outlook, and iOS dark mode.”
This starts a paid rendering job. The agent checks the job until it finishes, then returns a screenshot per client.
“Audit this before we send it.”
The audit returns readiness, check coverage, size metrics, and the findings to fix. A partial result is free and does not establish readiness.
“Send me a test.”
This sends a one-off test to your inbox and never touches your audience. Check your inbox after Brew accepts it.
“Check whether this lands in the inbox or spam.”
This is a seed send across real providers. It starts out queued or running, so ask the agent to check the results until the test completes.
“Validate the Newsletter subscribers audience before we send.”
The agent reads every page of the audience’s addresses, then checks them in batches of up to 100. Review the verdicts before sending. Validation doesn’t guarantee delivery. MCP Tools lists limits and costs.

5. Send It

Choose a sendable marketing domain and an opted-in audience, then ask the agent to prepare the send:
On OAuth and organization connections, the agent asks you to approve a production send first. Review the recipients, sender, subject, preview, and timing. After you approve, it repeats the same send with your approval attached. A brand API key skips Brew’s confirmation gate. Your working instructions still require approval before sending. MCP Authentication and Scoping describes the connection-specific behavior. Check the send’s status and your test inbox. An accepted send isn’t proof of inbox delivery.

6. Where This Goes Next

The same session can run the rest of your email program: Audiences. Save a filtered audience:
“Create an audience of contacts on the Pro plan who joined this quarter.”
Contact imports. The agent can import a CSV file or rows it already holds:
“Import this CSV of webinar sign-ups.”
Missing contacts are created and existing ones updated, and the batch appears in Import History. On OAuth and organization connections, the agent asks you to approve an import first. Check how many contacts it would add as subscribed before you approve. Automations. Build a flow, then test and publish it from chat:
“Build a 3-step welcome flow triggered by user signup.”
Audience automations. This follows the audience automation workflow, which ends by launching the run:
“Run this follow-up sequence for Newsletter subscribers.”
Review tests and a dry-run recipient count before approving the launch. Analytics. Next week, ask how a send did:
“How did the newsletter perform against our last three sends?”
The agent can return per-send stats, or the totals, rates, and timeseries the app shows. Design import. Converting one Figma frame is deterministic and free:
“Turn this Figma frame into an email.”
Images. The agent can host an image from a public URL:
“Host the image at https://example.com/hero.png in Brew.”
A local file takes a separate upload request first, then the same add step. That path needs an agent that can send file bytes. Attaching a file in chat alone does not complete the upload; Upload a Local Image covers the transfer. Send control. A gradual send already in flight can be paused and resumed:
“Pause the gradual send of the spring sale email.”
Canceling instead permanently stops the remaining deliveries. For the full tool list see MCP Tools, and for multi-step patterns see MCP Workflows. Wiring Brew into a coding agent that also builds your product? Use Brew with AI Agents covers that side. If your agent runs shell commands, the Brew CLI offers a terminal path for supported operations.

Troubleshooting

From an Agent or Code

Before translating this recipe to HTTP or the terminal, check which operations each interface offers. Some MCP tools combine several API operations, and some are MCP-only. MCP Tools lists HTTP equivalents where available. CLI Commands lists terminal operations, and Build with Brew compares the four interfaces.

Need Help?

Our team is ready to support you at every step of your journey with Brew. Choose the option that works best for you:

Search Documentation

Type in the “Ask any question” search bar at the top left to instantly find relevant documentation pages.

Ask ChatGPT or Claude

Click here to open the Copy page menu at the top of this page, then send the page to ChatGPT, Claude, or your editor.