Researches the keyword, writes the piece, publishes it, and audits what the page actually ships.
Built for: The one-person content team who owns the calendar, the CMS and the search rankings at the same time.
The button opens the checkout, where the 7 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.
Research keywords and search intent through Semrush and Ahrefs before the brief is written rather than after.
Publish to WordPress or Contentful from the same session that produced the draft.
Run a technical SEO audit against Search Console history and a first-party crawl, and list what is worth fixing.
Generate the images a post needs and check that the page is not shipping them four times too large.
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 keyword and competitive data the brief is argued from, rather than the writer's guess about what people search for.
The backlink and ranking side of the same question, for the pieces that are trying to win a term somebody already owns.
Posts, pages, media and custom types over the WordPress REST API — where most of this writing is actually published.
The structured CMS half, for teams whose site is a front end over content models rather than a blog.
Generates the header and inline images from the post's own text, so the visual is not a stock photograph chosen at the last minute.
Audits the published page's images — oversized files, wrong formats, natural against rendered size — which is a ranking factor and a bandwidth bill at once.
Merges Search Console history with a first-party crawl into one technical audit, which is the closest thing here to a full picture.
Turns the raw keyword data into intent and priority, which is the step that decides whether the piece was worth writing.
Repurposes the post into a captioned video, because the same research now has to appear on three surfaces instead of one.
The newsletter and lifecycle sends that carry the piece to the audience already subscribed, written to the same brief.
For content teams sitting on a storefront: the dead and duplicate products that quietly compete with the pages you are trying to rank.
For the long piece that has to stand up to scrutiny — a real survey with real citations, rather than five links found while drafting.
Checks what the published page does in a browser: the rendered markup, the redirect, the thing the CMS preview did not show.
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 |
|---|---|---|
| Semrush | Free | — |
| Ahrefs | Free | — |
| Wordpress | Free | — |
| Contentful | Free | — |
| Imagegen | Free | — |
| Imagedimensions | Free | — |
| Seo Audit Console | Free | — |
| Skills | ||
| Keyword Research | Free · context cost only | — |
| Super Video Maker | Free · context cost only | — |
| email-sequences | Free · context cost only | — |
| Shopify Catalog Cleanup | Free · context cost only | — |
| Literature Survey | Free · context cost only | — |
| Browser Automation with playwright-cli | Free · context cost only | — |
| Everything above | $0 of servers plus $0 of skills, the same in a quiet month and a busy one | $0/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months.
Install only these and the bill is nothing: 7 servers and 6 skills, and all 73 tools.
Nothing in this stack carries a call allowance, so nothing here can run out before the month does. The bill is decided when you install it, not when you use it.
The spend cap is one figure for the whole account, set in your dashboard and checked when an order is placed. On the call path what stops a retry loop is the plan's call allowance and its rate limit, and a refused call is never billed.
The steps below come before the install lines: what to decide and scope before connecting anything, in the order it matters. The lines themselves follow, part by part, for the client you pick.
npx mcprush@latest stack add content-seo writes all 7 servers into Claude Code’s config in one go — or run the lines below one by one. The 6 skills are not included — add them with lines 08–13.
SEMRUSH_API_KEY — Your Semrush API keyWP_URL — Your WordPress site URLWP_USERNAME — WordPress user nameWP_APP_PASSWORD — Application password (Users → Profile → Application Passwords)CONTENTFUL_MANAGEMENT_ACCESS_TOKEN — Contentful management token (Settings → CMA tokens)OPENAI_API_KEY — Your OpenAI API keyGOOGLE_APPLICATION_CREDENTIALS — Path to the Google service-account JSON key with Search Console accessSet them where you start Claude Code — export SEMRUSH_API_KEY=… in your shell profile on macOS and Linux, setx SEMRUSH_API_KEY "…" on Windows, then open a new terminal. Claude Code reads them at start; the config keeps only the names.
# 01 · Semrush
claude mcp add --scope user --env 'SEMRUSH_API_KEY=${SEMRUSH_API_KEY}' --transport stdio semrush-mcp '--' npx -y semrush-mcp
# 02 · Ahrefs
claude mcp add --scope user ahrefs-mcp '--' npx -y @ahrefs/mcp
# 03 · Wordpress
claude mcp add --scope user --env 'WP_URL=${WP_URL}' --env 'WP_USERNAME=${WP_USERNAME}' --env 'WP_APP_PASSWORD=${WP_APP_PASSWORD}' --transport stdio wordpress-mcp '--' npx -y @mangerik/wordpress-mcp
# 04 · Contentful
claude mcp add --scope user --env 'CONTENTFUL_MANAGEMENT_ACCESS_TOKEN=${CONTENTFUL_MANAGEMENT_ACCESS_TOKEN}' --transport stdio contentful-mcp '--' npx -y @contentful/mcp-server
# 05 · Imagegen
claude mcp add --scope user --env 'OPENAI_API_KEY=${OPENAI_API_KEY}' --transport stdio imagegen-mcp '--' npx -y imagegen-mcp
# 06 · Imagedimensions
claude mcp add --scope user imagedimensions-mcp '--' npx -y imagedimensions-mcp
# 07 · Seo Audit Console
claude mcp add --scope user --env 'GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS}' --transport stdio seo-audit-console-mcp '--' npx -y @houtini/seo-audit-console
# 08 · Keyword Research
npx mcprush@latest skill add kostja94/keyword-research
# 09 · Super Video Maker
npx mcprush@latest skill add bomx/super-video-maker
# 10 · email-sequences
npx mcprush@latest skill add rampstackco/email-sequences
# 11 · Shopify Catalog Cleanup
npx mcprush@latest skill add kgelster/shopify-catalog-cleanup
# 12 · Literature Survey
npx mcprush@latest skill add ai4s-research/literature-survey
# 13 · Browser Automation with playwright-cli
npx mcprush@latest skill add microsoft/browser-automation-with-playwright-clinpx).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 |
|---|---|---|
| Seo Audit Console | imported | 3 |
| Ahrefs | not imported | not recorded |
| Contentful | not imported | not recorded |
| Wordpress | 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 3 members of 7 have 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 team without an SEO subscription still gets meta tags, robots, sitemaps and keyword basics from the open toolkit, and gives up competitive data to do it.
Same job, different content platform — take the one your site already renders from and drop the other.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot rank a page. Everything here shortens the loop between writing and measuring; the ranking still belongs to the search engine.
It does not run your ad spend. This desk is organic — the paid side is a different budget and a different stack.
Nothing here approves publication. A draft goes live because a person said so, and the CMS credentials should reflect that.
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.
Drives the real interface, keeps the end-to-end suite current, and checks the things a screenshot does not show.
Reads the Figma file, builds the component, and ships the page without redrawing the design in CSS by eye.
Tools to inspect code changes, run checks and prepare a pull request review.