How does this differ from using an image editor or AI image generation?
It provides deterministic, configurable PNG generation via simple text prompts – ideal for rapid prototyping placeholder assets without manual design or generative AI overhead.
@crony-io
Basic information
An MCP (Model Context Protocol) server that generates advanced mock 2D PNG assets for games prototypes — directly from any MCP-compatible AI client such as Claude Desktop.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"2d-assets": {
"args": [
"-y",
"2d-assets-mcp"
],
"command": "npx",
"disabled": false
}
}
}Generates a single advanced custom mock 2D PNG asset (supports gradients, patterns, text rotation, transparency, and auto-scaling) for game prototypes. Embeds JSON metadata into the PNG (dimensions, color, shape, description) readable by read_image_metadata.
Generates multiple mock 2D PNG assets at once. Can create individual files, a spritesheet, Each PNG has embedded JSON metadata readable by read_image_metadata.
Reads the embedded JSON metadata from a PNG file generated by this MCP server. Returns the metadata object with dimensions, color, shape, description, etc.
An MCP server that generates advanced mock 2D PNG assets for game prototypes directly from any MCP-compatible AI client like Claude Desktop. It is engine-agnostic, supporting Godot, Unity, Unreal Engine, GameMaker, and more. Designed for developers to create placeholder sprites, UI elements, health bars, and spritesheets without opening an image editor.
Install via npx (no install: add {"command": "npx", "args": ["-y", "2d-assets-mcp"]} to your MCP client config) or install globally with npm/pnpm. Three tools are provided: generate_mock_asset, generate_mock_asset_batch, and read_image_metadata. Invoke by describing assets in natural language (e.g., “Create a 128×128 blue rounded-rectangle placeholder…”).
fillPercent and trackColor.fontSize.player_idle_128x128.png).It provides deterministic, configurable PNG generation via simple text prompts – ideal for rapid prototyping placeholder assets without manual design or generative AI overhead.
Node.js and an MCP-compatible client (e.g., Claude Desktop). It can run via `npx` without installation or

Built by movie lovers, for movie lovers and their assistants. SceneF puts every screen in California and Hawaii on one board — 33 regions, from San Francisco's single-screen neighborhood houses and nightly repertory cale

Exercise videos, workouts and training programs for AI agents and apps: 1,413+ exercises with professional HD video, instructions and muscle data, plus workout and program generation and nutrition tools. Hosted MCP, no i

A library of conversion components for e-commerce, built on A/B tested mechanics and handed straight to your coding agent. 65 pieces drawn from mechanics that have been A/B tested in real stores: cart drawer with the ups

Instagram + TikTok content tools inside your AI: download HD posts/reels/carousels, view Instagram stories anonymously, AI-transcribe videos (100+ languages, SRT/VTT/TXT). Requires a Repost PRO subscription.

Ask your AI assistant about your Angelcam security cameras: list cameras and locations, check which are online, take live or recorded snapshots, browse recordings and review security incidents. Read-only; sign in with yo
Comments