Home All stacks
StacksThe Growth Marketing Stack

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.

🐘💬🔮📝🔥+1
Stack · 6 MCPs

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 github

One 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)

🐘

Postgres

Product analytics warehouse (Amplitude/PostHog export)

View
💬

Slack

Growth channel + cross-team coms

View
🔮

Perplexity

Market research & playbooks

View
📝

Notion

Experiment log & growth docs

View
🔥

Firecrawl

Competitor landing & content scraping

View
🐙

GitHub

Landing page code & A/B test infra

View

What this stack lets you do

Experiment ideation from competitor research

See recipe
  1. 1Firecrawl scrapes 10 competitor landing pages
  2. 2Perplexity analyzes positioning + headline patterns
  3. 3Claude drafts 5 experiment hypotheses in Notion
  4. 4Top pick moved to 'In Progress' with full brief

Landing page A/B test

  1. 1Notion experiment doc → Claude reads hypothesis
  2. 2Writes variant B component in GitHub (opens PR)
  3. 3Vercel preview auto-deploys for review
  4. 4PostHog event tracking wired into the variant
  5. 5Test goes live; Postgres query summarises results after 7 days
  6. 6Winner announced in Slack

Monthly growth retrospective

  1. 1Claude queries Postgres for all experiments last month
  2. 2Pulls hypothesis + result from Notion for each
  3. 3Synthesizes lessons learned ('what worked, what didn't')
  4. 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.

Other stacks

The SaaS Starter Stack

Everything to launch a B2B SaaS in a weekend

6 MCPs

The AI Agent Builder Stack

Search, scrape, memory, and cache — the infrastructure every agent needs

6 MCPs

The Content Ops Stack

Research, write, voice, publish — the content pipeline in 5 MCPs

5 MCPs

Install this stack

$ mcpizy install postgres slack perplexity notion firecrawl github

🐘Postgres💬Slack🔮Perplexity📝Notion
Browse all MCPs