Writes the issue, schedules it, keeps the list healthy and makes sure the mail reaches the inbox rather than the spam folder.
Built for: The one person who writes the newsletter, runs the lifecycle emails and gets asked why open rates fell.
The button opens the checkout, where the 2 servers and 6 skills are listed one by one. Every member is free, so the checkout lists them and asks for no card.
The reason to buy a stack rather than five listings: each line below needs more than one member connected at the same time.
Draft an issue in your voice, give three subject lines, and save it as a Buttondown draft scheduled for the usual slot.
Pull the analytics for the last issues and say which ones held opens and clicks.
Write the welcome and win-back sequences and set them up as Loops campaigns for the product side.
Check the sending domain against SPF, DKIM and DMARC practice when mail starts landing in spam.
What each part contributes, and why it was picked over the obvious alternative. Prices and permissions are read from the listings, so nothing here can disagree with the catalogue.
The Buttondown API: drafts, scheduling, sending, subscribers, tags and per-email analytics.
Loops' hosted server for contacts, mailing lists, campaigns and transactional email — the product emails that are not the newsletter.
Anthropic's marketing skill for newsletters, posts and landing pages with channel-specific formatting and subject-line options.
Onboarding, nurture and win-back sequences with timing, branching and exit conditions — a flow, not a pile of sends.
Resend's guide to SPF, DKIM and DMARC, list capture, compliance (CAN-SPAM, GDPR, CASL) and accessible email.
Diagnoses why mail goes to spam or bounces — authentication, IP warm-up, list hygiene — with or without SendGrid.
HTML email templates as React components, rendered to markup that survives the major clients.
Applies your voice and style guide across issues, so the tenth one sounds like the first.
Every member is free, so the monthly figure is $0 whatever you do with the stack: nothing here is billed by the call, and only adding a paid member could change it.
| Part | What you are paying for | Monthly, as quoted |
|---|---|---|
| Buttondown | Free | — |
| Loops | Free | — |
| Skills | ||
| Draft Content | Free · context cost only | — |
| Email Sequence | Free · context cost only | — |
| email-best-practices | Free · context cost only | — |
| twilio-sendgrid-deliverability-advisor | Free · context cost only | — |
| react-email | Free · context cost only | — |
| Brand Voice | Free · context cost only | — |
| Everything above | $0 of servers plus $0 of skills, the same in a quiet month and a busy one | $0/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months.
Install only these and the bill is nothing: 2 servers and 6 skills, and all 15 tools.
Nothing in this stack carries a call allowance, so nothing here can run out before the month does. The bill is decided when you install it, not when you use it.
The spend cap is one figure for the whole account, set in your dashboard and checked when an order is placed. On the call path what stops a retry loop is the plan's call allowance and its rate limit, and a refused call is never billed.
The steps below come before the install lines: what to decide and scope before connecting anything, in the order it matters. The lines themselves follow, part by part, for the client you pick.
npx mcprush@latest stack add newsletter-desk writes all 2 servers into Claude Code’s config in one go — or run the lines below one by one. The 6 skills are not included — add them with lines 03–08.
# 01 · Buttondown
claude mcp add --scope user buttondown-mcp '--' npx -y buttondown-mcp
# 02 · Loops
claude mcp add --scope user --transport http loops-mcp https://mcp.loops.so
# 03 · Draft Content
npx mcprush@latest skill add anthropics/draft-content
# 04 · Email Sequence
npx mcprush@latest skill add anthropics/email-sequence
# 05 · email-best-practices
npx mcprush@latest skill add resend/email-best-practices
# 06 · twilio-sendgrid-deliverability-advisor
npx mcprush@latest skill add twilio/twilio-sendgrid-deliverability-advisor
# 07 · react-email
npx mcprush@latest skill add resend/react-email
# 08 · Brand Voice
npx mcprush@latest skill add anthropics/brand-voicenpx).Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.Nothing is connected until you approve it in Claude Code. mcprush is not in the path and meters nothing here.
Installed together, these tool surfaces add up. It is the first thing a security reviewer asks for, so what has been counted — and what nobody has counted yet — is on the page rather than in a PDF.
| Member | Tool surface | Write tools |
|---|---|---|
| Buttondown | imported | 7 |
| Loops | not imported | not recorded |
A stack's blast radius is the union of its members, not the worst of them. That union cannot be taken here, because 1 member of 2 has no imported tool surface — so the figure a review asks for is missing rather than low, and a member marked not imported is one nobody has counted rather than one that cannot write.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
A list that lives on Mailchimp is read through a Mailchimp server instead — campaigns, reports, members and automations. It reads and reports; sending stays in Mailchimp.
Written by the maintainer, kept on the page rather than in a support thread.
It does not buy or scrape lists. Every address here came through your own sign-up form, and the compliance skill is there to keep it that way.
Deliverability advice cannot change your sending reputation overnight; warm-up and list hygiene take weeks.
It covers Buttondown for the newsletter. A publication on another platform needs a different server.
A stack has an owner: whoever keeps it re-checks the combination when a member changes, and the members themselves are published by the people named on each row.
Tools to inspect code changes, run checks and prepare a pull request review.
Tools to investigate a bug report and work toward a reproducible test case.
Tools to investigate alerts, check recent changes and follow the runbook.