Design UI projects 🎨🖼️ with Google Stitch via Telegram using MCP and Gemini AI
Ready for 3.0What this workflow does
This AI workflow has 20 nodes and runs on Telegram events (message) (plus 1 other trigger). Along the way it connects Google Gemini Chat Model, MCP Client, Perplexity and Telegram.
How it runs
Trigger: On Telegram events (message) (plus 1 other trigger).
- Code: runs custom JavaScript code
- Google Stitch Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 7 tools (Get screen, Get Project, List screen, List projects…); memory: Simple Memory
- Search with MCP? (If): checks a condition and branches into true / false
- is Telegram? (If): checks a condition and branches into true / false
- Get Text (Edit Fields (Set)): sets 2 fields: chatInput, sessionId
- From MD to HTML (Basic LLM Chain): sends a prompt to an LLM, with model: Google Gemini Chat Model
- Clean query (Code): runs custom JavaScript code
- Send a text message (Telegram): uses Telegram
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (12)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - Perplexity Tool
n8n-nodes-base.perplexityTool - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - Telegram Trigger
n8n-nodes-base.telegramTrigger - Edit Fields (Set)
n8n-nodes-base.set - Telegram
n8n-nodes-base.telegram - AI Agent
@n8n/n8n-nodes-langchain.agent - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
From the author
This workflow implements an AI-powered design and prototyping assistant that integrates Telegram, Google Gemini, and Google Stitch (MCP) to enable conversational UI generation and project management. Supported actions include: Creating new design projects…