image-gen
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@image-gengenerate an image of a futuristic city skyline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
image-gen — Agent's Paintbrush
Marketing site + waitlist API for image-gen, an MCP server that gives AI coding agents a paintbrush (ChatGPT-in-browser image gen, no OpenAI API key).
Built for The Zerops Challenge (WeMakeDevs).
Architecture (3 Zerops services)
Service | Type | Role |
| Node.js 22 (TanStack Start SSR) | Marketing frontend + same-origin API routes |
| Node.js 22 | Dedicated HTTP API for waitlist / stats / health |
| PostgreSQL 16 | Waitlist signups + site counters |
The MCP server itself runs on the user's machine. Zerops hosts this website, the API, and Postgres.
Related MCP server: create-image-mcp
Local development
npm install
# optional local Postgres
export DATABASE_URL=postgres://postgres:postgres@localhost:5432/imagegen
npm run dev # web on :3000
npm run start:api # api on :3000 (use another PORT if both run)Deploy on Zerops
# once
npm i -g @zerops/zcli
zcli login <token>
# create project + services
zcli project project-import ./zerops-import.yml
zcli project scope <project-id>
# push both runtimes
zcli push --setup web
zcli push --setup apiSee DEPLOY_ZEROPS.md for env vars and endpoints.
API
GET /api/public/healthPOST /api/public/waitlist—{ email, note? }GET /api/public/statsPOST /api/public/click
Stack
TanStack Start + React 19 + Tailwind CSS 4
Node.js HTTP API (
api/server.mjs)PostgreSQL via
pgZerops for build, deploy, networking, SSL
AI Usage
Lovable made initial design ( completely revamped from it tbh u cant even see trace of me using it now coz i didnt like lovable's design ) , later cursor helped me further refine the design , mcp was designed by scratch by me and then refined using cursor still refining the website more but yeah mcp end to end fully works , i first designed a rough wireframe like i usually do on figma then proceeded to design in and replicate it on dev platform using cursor
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Flux AI image generation
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
An MCP server that integrates with Discord to provide AI-powered features.
MCP server for NanoBanana AI image generation and editing
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceMCP server that lets AI agents use your real browser as an API, accessing any website with your login state, no keys or scrapers needed.1MIT
- AlicenseAqualityDmaintenanceAn MCP server that generates and edits images using OpenAI's GPT Image model, allowing users to create images from text descriptions and edit existing images through natural language.13 npmMIT
- FlicenseAqualityDmaintenanceAn MCP server that enables AI coding agents to create pixel art programmatically by providing canvas manipulation tools and PNG export.1018 npm2-
- AlicenseNot gradedqualityCmaintenanceMCP server for AI-powered image generation using OpenAI's gpt-image-1 and gpt-image-2 models with advanced text rendering and native transparency support.38 npm1MIT