TL;DR
The Growth Stack is 6 MCPs (Postgres, Slack, Perplexity, Notion, Firecrawl, GitHub) that cover research → experiment → analysis for a growth team. Ideas come from Perplexity + Firecrawl; implementation runs through GitHub + Notion; results get analyzed in Postgres and announced in Slack. Shipping 2–3x more experiments per month is typical.
The Growth Marketing Stack
Analytics, research, notes, and copy — the growth team's AI backbone
Install the whole stack
$ mcpizy install postgres slack perplexity notion firecrawl githubOne command installs and configures all 6 MCPs for Claude Code, Cursor, Windsurf, or any MCP-compatible client.
Why this stack?
Growth teams are research-driven and experiment-heavy. The bottlenecks are: finding what to test (research), running the test (implementation), and analysing results (analytics). This stack covers all three. Perplexity + Firecrawl drive research; GitHub + Notion manage implementation and experiment docs; Postgres + Slack analyze and broadcast results.
The multiplier: a growth team with this stack runs 2–3x more experiments per month, because the ideation-to-implementation friction collapses. Claude drafts the experiment doc, writes the landing page variant, opens the PR, sets up the PostHog event, and ships the Slack update — all in one session.
MCPs in this stack (6)
What this stack lets you do
Experiment ideation from competitor research
See recipe- 1Firecrawl scrapes 10 competitor landing pages
- 2Perplexity analyzes positioning + headline patterns
- 3Claude drafts 5 experiment hypotheses in Notion
- 4Top pick moved to 'In Progress' with full brief
Landing page A/B test
- 1Notion experiment doc → Claude reads hypothesis
- 2Writes variant B component in GitHub (opens PR)
- 3Vercel preview auto-deploys for review
- 4PostHog event tracking wired into the variant
- 5Test goes live; Postgres query summarises results after 7 days
- 6Winner announced in Slack
Monthly growth retrospective
- 1Claude queries Postgres for all experiments last month
- 2Pulls hypothesis + result from Notion for each
- 3Synthesizes lessons learned ('what worked, what didn't')
- 4Posts summary to Slack + archives in Notion
Estimated value
Replaces ~$500/mo of growth tooling (Visualping, Klue starter, research VA hours) for a 3-person growth team. Bigger win: experiment velocity doubles, which compounds into faster CAC reduction.
Frequently asked questions
Do I need PostHog/Amplitude MCP too?
PostHog MCP exists (community). Amplitude MCP is in early beta. For now, the Postgres MCP in this stack assumes you export product analytics to Postgres via Fivetran/RudderStack. Direct MCPs will add cleaner event-level access when they mature.
Can Claude actually write A/B test variants?
Yes — given a design spec (Figma/Notion) and the existing component code (GitHub MCP), Claude writes the variant, wires PostHog events, and opens the PR. Most growth engineers cut variant-creation time by 70%.
What about Webflow or Framer sites?
Both have community MCPs in early stages. For production-ready growth sites, keep landing pages in GitHub (Next.js/Astro) for cleanest MCP integration. Webflow MCP works but is limited today.
Does this work for B2C growth, not just B2B?
Yes — the stack is domain-agnostic. B2C teams often add a creative/ads MCP (Meta Ads MCP, TikTok Ads MCP) for paid-heavy work. The core 6 stay the same.
How does this compare to a full experimentation platform like Optimizely?
Optimizely gives you the runtime traffic-splitting infra. This stack gives you the ideation + analysis infra. They complement each other — use Optimizely for sophisticated splits, MCPs for the 'Claude writes the variant' step.