Image Gen MCP server
{
"mcpServers": {
"nuverlabs-image-gen": {
"command": "npx",
"args": [
"-y",
"@nuver-labs/image-gen-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "<gemini_api_key>",
"OPENAI_API_KEY": "sk-..."
}
}
}
}{
"mcpServers": {
"nuverlabs-image-gen": {
"command": "npx",
"args": [
"-y",
"@nuver-labs/image-gen-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "<gemini_api_key>",
"OPENAI_API_KEY": "sk-..."
}
}
}
}{
"mcpServers": {
"nuverlabs-image-gen": {
"command": "npx",
"args": [
"-y",
"@nuver-labs/image-gen-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "<gemini_api_key>",
"OPENAI_API_KEY": "sk-..."
}
}
}
}{
"servers": {
"nuverlabs-image-gen": {
"command": "npx",
"args": [
"-y",
"@nuver-labs/image-gen-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "${input:gemini_api_key}",
"OPENAI_API_KEY": "${input:openai_api_key}"
}
}
},
"inputs": [
{
"id": "gemini_api_key",
"type": "promptString",
"description": "Gemini api key",
"password": true
},
{
"id": "openai_api_key",
"type": "promptString",
"description": "Openai api key",
"password": true
}
]
}{
"mcpServers": {
"nuverlabs-image-gen": {
"command": "npx",
"args": [
"-y",
"@nuver-labs/image-gen-mcp@latest"
],
"env": {
"GEMINI_API_KEY": "<gemini_api_key>",
"OPENAI_API_KEY": "sk-..."
}
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsoninstall npx -y @nuver-labs/image-gen-mcpversion 0.2.1
What it does
MCP server for generating and editing images using Google Gemini or OpenAI image models, with your own API keys. Integrates with coding agents to create and modify images directly in your project.
- Generate images from text prompts (blog covers, logos, illustrations) and save them to your project for the agent to iterate on.
- Edit existing images by applying text-based modifications or combining multiple images as references.
- Create multiple variations of an image in different aspect ratios and quality levels for design drafts.
Tools this server exposes
| Tool | Does |
|---|---|
| generate_image | Create one or more images from a text prompt, with options for aspect ratio, model selection, quality, and output path. |
| edit_image | Modify existing images using text instructions, optionally referencing other images, without overwriting source files. |
| list_capabilities | Report which providers are configured, available models, supported options, and output directory rules. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.