Back to Blogs
How We Built Native MCP Support Into a Rich Text Editor (Architecture Deep-Dive)

Total Views

20

Read Time

48 min read

Updated On

16.11.2026

Try it yourself —
EDDYTERthe editor rendering this page
Blogs

Introduction

Nov 16, 2026

How We Built Native MCP Support Into a Rich Text Editor (Architecture Deep-Dive)

WYSIWYG Editorsmcp architecturerich text editor mcpnative mcp editormodel context protocol editor implementationeddyter mcpmcp session managementmcp streamable httpmcp securityeditor sdk architecturemcp client server dualmcp 2026

Engineering deep-dive on building native MCP support (client + server) into a Lexical-based rich text editor. 6-layer architecture, hard trade-offs, code.

TL;DR

Native MCP architecture for a Lexical-based rich text editor: 6 layers, backend MCP client (not browser), WebSocket MCP server for the document, scoped OAuth, CRDT conflict resolution. 14 weeks total.

How We Built Native MCP Support Into a Rich Text Editor (Architecture Deep-Dive)

Content

Shreya Taneja

Written by

Shreya Taneja

Project Manager