HTML Email Playbook
Teaches AI to write HTML email that renders in Outlook, Gmail, and Apple Mail. 19 rules, 6 components.
README
Osama Hassouna · Docs
Source for docs.osamahassouna.com — an engineering reference hub I keep open while building. Currently one guide is live, with more landing as I write them.
Live now
HTML Email Playbook
A working reference for hand-building HTML email templates that render reliably across Outlook (Windows desktop, 2007 through 365), Gmail web + mobile, Apple Mail, Yahoo Mail, and the long tail of clients that haven't moved past 2007.
Covers:
- Structure — doctype, head boilerplate, body container, header / body / footer organization
- Components — bulletproof CTA buttons (with Outlook VML fallback), spacing patterns, images, inline icons, background images, text
- Compatibility — Outlook MSO conditional comments, RTL languages, hybrid responsive layouts
- Production — Gmail 102KB clipping, dark mode, preheader text
- AI Generation — rules and patterns for AI tools that generate playbook-compliant email HTML
Read it: docs.osamahassouna.com/email-playbook/
There's also a Playground at /email-playbook/playground/ with a live editor, instant preview, and a "From Image" tab that converts a design screenshot into playbook-compliant HTML.
Use the playbook in your AI workflow
The playbook is published as an MCP server + terminal CLI so AI clients (Claude Desktop, Cursor, Cline, etc.) can pull rules and component patterns directly into their reasoning. The model calls structured tools to fetch the exact patterns from the playbook instead of guessing from training data.
npm install -g email-playbook-mcp
Setup, tool reference, and Claude Desktop / Cursor config snippets:
docs.osamahassouna.com/email-playbook/cli/
There's also a hosted JSON-RPC endpoint at docs.osamahassouna.com/api/mcp if you'd rather not install anything.
License
MIT. Playbook content © Osama Hassouna · osamahassouna.com
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.