MCP Asset Generator
The MCP Asset Generator server allows you to generate image assets using OpenAI's GPT by:
Creating images based on text descriptions (prompts)
Saving generated images to specified absolute file paths
Customizing image properties including size and quality
Integrating seamlessly into development workflows for game or web projects
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., "@MCP Asset Generatorgenerate a pixel art spaceship for my mobile game"
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.
mcp-asset-gen
This tool allows Claude to speak to OpenAI, and use gpt-image-1 to generate image assets. This can be pretty useful for game or web development, when you need to print individual assets.
Requirements
Node
An OpenAI API Key
Note that this requires an organization, with ID verification at the moment.
Installation
Get an API KEY from the OpenAI website.
Export it in your shell as API_KEY.
export API_KEY=sk-proj-....Then, paste this into that same shell:
jq --arg apiKey "$API_KEY" \
'.mcpServers = (.mcpServers // {}) |
.mcpServers["mcp-asset-gen"] = {
type: "stdio",
command: "npx",
args: ["mcp-asset-gen"],
env: { API_KEY: $apiKey }
}' ~/.claude.json > ~/.claude.tmp && mv ~/.claude.tmp ~/.claude.jsonYou're done! Ask Claude to generate you an image for something, and you'll see
> generate a small logo image that i could use for my arcade game
I'll generate a logo for your arcade game. Please provide a more specific description of what you'd like to see in the logo (colors, style,
game theme, etc.) for better results.
> It should look like an old school pacman machine (liek a wooden arcade machine)
⏺ mcp-asset-gen:generateImag(outputPathAbsolute: "/Users/jbrower/projects/mcp-asset-gen/arcade-logo.png", prompt: "An old school wooden arcade…
(MCP) machine logo in the style of Pacman, with retro colors and pixelated elements, top-down view of the cabinet,
nostalgic arcade gaming feel, vibrant colors against dark background", quality: "high", size: "1024x1024")
⎿ The image is now available at /Users/jbrower/projects/mcp-asset-gen/arcade-logo.png.
⏺ Generated arcade logo saved to /Users/jbrower/projects/mcp-asset-gen/arcade-logo.pngAvailable Tools
1 toolgenerateImageD
| Name | Required | Description | Default |
|---|---|---|---|
| outputPathAbsolute | Yes | The absolute path where the image should be written out. | |
| prompt | Yes | Text description of the desired image content | |
| quality | No | The quality of the image. | |
| size | No | Size of the generated image |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
generateImage
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly implied by its name even without a description.
Single tool uses a clear camelCase convention, and there are no other tools to introduce inconsistencies. The name is readable and follows a logical pattern.
A single tool feels too few for a server called 'Asset Generator,' which implies a broader suite of asset-creation capabilities. This is under-scoped and likely limits practical use.
With only generateImage and no other operations, the server covers a tiny slice of asset generation. There is no way to handle other asset types or perform related tasks, making the surface severely incomplete for the stated domain.
Maintenance
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server for OpenAI Sora AI video generation
MCP server for NanoBanana AI image generation and editing
MCP server for Grok Imagine AI video generation
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that turns Claude into a full image production studio, enabling creation, editing, resizing, and brand-consistent asset generation across multiple platforms.6MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables Claude Code to generate images using Google's Gemini image generation models.MIT
- 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.17 npmMIT
- AlicenseNot gradedqualityDmaintenanceA local MCP server that enables Claude to generate images using the OpenAI API.5 npmMIT