Which integrations are available for this server?

Allows generating images using Google's Gemini AI models with support for multiple providers, aspect ratios, and resolutions.

How do I use @genoooool/mcp-image-generator?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@genoooool/mcp-image-generator Generate a photorealistic image of a cat sitting on a windowsill." 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.

@genoooool/mcp-image-generator

by genoooool

Overview Schema Related Servers Score Discussions

TypeScript

Remote

@genoooool/mcp-image-generator

This is an MCP (Model Context Protocol) server for AI image generation with multi-provider support.

Features

Multi-provider support: Switch between Yunwu, Gemini Official, and custom Gemini providers without changing code
Environment variable configuration: All provider settings controlled via environment variables
Flexible output: Save images to custom directories with custom filenames
Multiple aspect ratios: Support for 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9
Resolution control: 1K, 2K, 4K resolution options (default: 2K)
Error handling: Comprehensive error messages with HTTP status codes and response details
Timeout support: Configurable request timeout (default: 60s)

Related MCP server: Gemini Image MCP

Supported MCP Clients

This MCP server works with:

Claude Desktop
Claude Code CLI
OpenCode
Codex
Any MCP-compatible client

Installation

Option 1: NPX (Recommended - No installation required)

npx -y @genoooool/mcp-image-generator

Option 2: Global Install

npm install -g @genoooool/mcp-image-generator

Option 3: Local Install

# Clone or download the repository
cd /path/to/project

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Environment Variables

Variable	Required	Description	Default
`IMAGE_PROVIDER`	Yes	Provider type: `yunwu`, `gemini_official`, or `custom_gemini`	-
`IMAGE_BASE_URL`	Depends on provider	Override default base URL	Provider-specific
`IMAGE_AUTH_TYPE`	No	Auth type: `bearer` or `apikey`	Provider-specific
`IMAGE_TOKEN`	Yes for bearer auth	Bearer token for authentication	-
`IMAGE_API_KEY`	Yes for apikey auth	API key for authentication	-
`IMAGE_OUT_DIR`	No	Default output directory for images	`./output`
`IMAGE_REQUEST_TIMEOUT`	No	Request timeout in milliseconds	`60000`

How to Switch Provider

1. Using Yunwu Provider

Set the following environment variables:

export IMAGE_PROVIDER=yunwu
export IMAGE_TOKEN=your_yunwu_token
export IMAGE_BASE_URL=https://yunwu.ai  # Optional, this is the default
export IMAGE_OUT_DIR=./images  # Optional

2. Using Gemini Official Provider

Set the following environment variables:

export IMAGE_PROVIDER=gemini_official
export IMAGE_API_KEY=your_gemini_api_key
export IMAGE_BASE_URL=https://generativelanguage.googleapis.com  # Optional, this is the default
export IMAGE_OUT_DIR=./images  # Optional

Note: Gemini Official API key authentication uses query parameter ?key= for REST API requests to generateContent endpoints.

3. Using Custom Gemini Provider

Set the following environment variables:

export IMAGE_PROVIDER=custom_gemini
export IMAGE_BASE_URL=https://your-custom-provider.com  # Required
export IMAGE_API_KEY=your_api_key  # Or use IMAGE_TOKEN with IMAGE_AUTH_TYPE=bearer
export IMAGE_AUTH_TYPE=apikey  # Optional: 'bearer' or 'apikey'
export IMAGE_OUT_DIR=./images  # Optional

MCP Client Configuration

Claude Desktop

Configuration File Location

Claude Desktop loads MCP configuration from:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Configuration Format

Add the MCP server to your configuration file:

{
  "mcpServers": {
    "image-generator-yunwu": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_yunwu_token",
        "IMAGE_OUT_DIR": "./images"
      }
    },
    "image-generator-gemini": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "gemini_official",
        "IMAGE_API_KEY": "your_gemini_api_key",
        "IMAGE_OUT_DIR": "./images"
      }
    },
    "image-generator-custom": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "custom_gemini",
        "IMAGE_BASE_URL": "https://your-custom-provider.com",
        "IMAGE_API_KEY": "your_api_key",
        "IMAGE_AUTH_TYPE": "apikey",
        "IMAGE_OUT_DIR": "./images"
      }
    }
  }
}

Using Global Installation

If you installed globally:

{
  "mcpServers": {
    "image-generator": {
      "command": "mcp-image-generator",
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

Using Local Installation

If you cloned the repository:

Windows:

{
  "mcpServers": {
    "image-generator": {
      "command": "node",
      "args": ["C:\\path\\to\\project\\dist\\index.js"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

macOS/Linux:

{
  "mcpServers": {
    "image-generator": {
      "command": "node",
      "args": ["/path/to/project/dist/index.js"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

Claude Code CLI

Configuration File Location

Claude Code CLI loads MCP configuration from:

Windows: %USERPROFILE%\.claude\config.json
macOS/Linux: ~/.claude/config.json

Configuration Format

Add the MCP server to your configuration file:

{
  "mcpServers": {
    "image-generator-yunwu": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_yunwu_token",
        "IMAGE_OUT_DIR": "./images"
      }
    },
    "image-generator-gemini": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "gemini_official",
        "IMAGE_API_KEY": "your_gemini_api_key",
        "IMAGE_OUT_DIR": "./images"
      }
    },
    "image-generator-custom": {
      "command": "npx",
      "args": ["-y", "@genoooool/mcp-image-generator"],
      "env": {
        "IMAGE_PROVIDER": "custom_gemini",
        "IMAGE_BASE_URL": "https://your-custom-provider.com",
        "IMAGE_API_KEY": "your_api_key",
        "IMAGE_AUTH_TYPE": "apikey",
        "IMAGE_OUT_DIR": "./images"
      }
    }
  }
}

Using Global Installation

If you installed globally:

{
  "mcpServers": {
    "image-generator": {
      "command": "mcp-image-generator",
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

Using Local Installation

If you cloned the repository:

Windows:

{
  "mcpServers": {
    "image-generator": {
      "command": "node",
      "args": ["C:\\path\\to\\project\\dist\\index.js"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

macOS/Linux:

{
  "mcpServers": {
    "image-generator": {
      "command": "node",
      "args": ["/path/to/project/dist/index.js"],
      "env": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_token"
      }
    }
  }
}

OpenCode

Configuration File Location

OpenCode loads MCP configuration from the following locations (in order of precedence):

Global config: ~/.config/opencode/opencode.json
Custom config: OPENCODE_CONFIG environment variable
Project config: opencode.json in project root

Configuration Format

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "image-generator-yunwu": {
      "type": "local",
      "command": ["npx", "-y", "@genoooool/mcp-image-generator"],
      "enabled": true,
      "environment": {
        "IMAGE_PROVIDER": "yunwu",
        "IMAGE_TOKEN": "your_yunwu_token",
        "IMAGE_OUT_DIR": "./images"
      }
    },
    "image-generator-gemini": {
      "type": "local",
      "command": ["npx", "-y", "@genoooool/mcp-image-generator"],
      "enabled": true,
      "environment": {
        "IMAGE_PROVIDER": "gemini_official",
        "IMAGE_API_KEY": "your_gemini_api_key",
        "IMAGE_OUT_DIR": "./images"
      }
    }
  }
}

Codex

Configuration File Location

Codex loads MCP configuration from the following locations:

Global config: ~/.config/codex/config.toml
Project config: codex.toml in project root

Configuration Format

[mcp_servers.image_yunwu]
command = "npx"
args = ["-y", "@genoooool/mcp-image-generator"]

[mcp_servers.image_yunwu.env]
IMAGE_PROVIDER = "yunwu"
IMAGE_TOKEN = "your_token"
IMAGE_OUT_DIR = "./images"

[mcp_servers.image_gemini]
command = "npx"
args = ["-y", "@genoooool/mcp-image-generator"]

[mcp_servers.image_gemini.env]
IMAGE_PROVIDER = "gemini_official"
IMAGE_API_KEY = "your_gemini_api_key"
IMAGE_OUT_DIR = "./images"

[mcp_servers.image_custom]
command = "npx"
args = ["-y", "@genoooool/mcp-image-generator"]

[mcp_servers.image_custom.env]
IMAGE_PROVIDER = "custom_gemini"
IMAGE_BASE_URL = "https://your-custom-provider.com"
IMAGE_API_KEY = "your_api_key"
IMAGE_AUTH_TYPE = "apikey"
IMAGE_OUT_DIR = "./images"

Tool Usage

`generate_image`

Generate an image using AI models.

Parameters

Parameter	Type	Required	Default	Description
`model`	string	No	`gemini-3-pro-image-preview`	Model to use for generation
`prompt`	string	Yes	-	The prompt for image generation
`aspect_ratio`	string	No	`1:1`	Aspect ratio: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`
`image_size`	string	No	`2K`	Resolution: `1K`, `2K`, `4K`
`out_dir`	string	No	`./output`	Directory to save the image
`filename`	string	No	`timestamp.png`	Custom filename

Return Value

{
  "url": "string",
  "file_path": "string | null",
  "provider": "string"
}

Note: For Yunwu provider, if the response does not include a URL field, only file_path will be returned and url will be empty.

Example Usage

Example 1: Generate a simple image

Input:

{
  "prompt": "A beautiful sunset over the ocean",
  "aspect_ratio": "16:9",
  "image_size": "2K"
}

Output:

{
  "url": "",
  "file_path": "./images/20260111_034500.png",
  "provider": "yunwu"
}

Example 2: Generate with custom filename

Input:

{
  "prompt": "A futuristic cityscape at night",
  "model": "gemini-3-pro-image-preview",
  "aspect_ratio": "1:1",
  "out_dir": "./my_images",
  "filename": "cityscape.png"
}

Output:

{
  "url": "",
  "file_path": "./my_images/cityscape.png",
  "provider": "gemini_official"
}

Example 3: Generate with direct URL (if supported)

Input:

{
  "prompt": "A peaceful mountain landscape",
  "aspect_ratio": "4:3",
  "image_size": "1K"
}

Output:

{
  "url": "https://cdn.example.com/images/abc123.png",
  "file_path": null,
  "provider": "yunwu"
}

Development

Build

npm run build

Development Mode (with auto-reload)

npm run dev

Manual Testing

You can test the server manually by running:

IMAGE_PROVIDER=yunwu \
IMAGE_TOKEN=your_token \
node dist/index.js

Then send JSON-RPC messages via stdin.

Provider Details

Yunwu Provider

Endpoint: POST https://yunwu.ai/v1beta/models/{model}:generateContent
Authentication: Bearer token via Authorization: Bearer {token} header
Response Handling:
- If response contains fileData.uri, returns the URL in url field
- If response contains inlineData.data, decodes base64 and saves to local file
- If no URL is available, url will be empty and only file_path is guaranteed

Gemini Official Provider

Endpoint: POST https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent?key={api_key}
Authentication: API key via query parameter ?key= in the URL
Response Handling: Same as Yunwu provider

Custom Gemini Provider

Endpoint: Configurable via IMAGE_BASE_URL
Authentication: Supports both bearer token and API key based on IMAGE_AUTH_TYPE
- bearer: Authorization: Bearer {token} header
- apikey: ?key={api_key} query parameter

Error Handling

The server returns detailed error messages when issues occur:

HTTP errors: Includes HTTP status code and response body
Validation errors: Includes field names and validation messages
Configuration errors: Clearly indicates missing required environment variables

Example error response:

Yunwu API error (401): {"error": "Invalid token"}

Troubleshooting

"IMAGE_PROVIDER environment variable is required"

Make sure you set the IMAGE_PROVIDER environment variable.

"IMAGE_TOKEN is required when IMAGE_AUTH_TYPE=bearer"

You're using bearer auth type but didn't provide a token. Either:

Set IMAGE_TOKEN environment variable
Change to apikey auth type and set IMAGE_API_KEY

"Unable to extract image from response"

The API response format may have changed. Check the provider's API documentation.

Timeout errors

Increase the timeout by setting IMAGE_REQUEST_TIMEOUT:

export IMAGE_REQUEST_TIMEOUT=120000  # 120 seconds

Claude Code doesn't show the MCP server

Make sure you've restarted Claude Code after editing the config file
Check that the configuration file path is correct for your OS
Verify the command works in your terminal (e.g., run npx -y @genoooool/mcp-image-generator)
Check Claude Code logs for error messages

License

MIT

Author

genoooool

Available Tools

1 tool

generate_imageB

Generate an image using AI models. Supports multiple providers (Yunwu, Gemini Official, Custom). Provider is configured via IMAGE_PROVIDER environment variable.

ParametersJSON Schema

Name	Required	Description
`model`	No	Model to use for generation (default: gemini-3-pro-image-preview)
`prompt`	Yes	The prompt for image generation
`out_dir`	No	Directory to save the image (optional)
`filename`	No	Custom filename (optional, default: timestamp.png)
`image_size`	No	Resolution of the generated image (default: 2K)
`aspect_ratio`	No	Aspect ratio of the generated image (default: 1:1)

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations and no output schema, the description carries the full burden for behavioral disclosure. It reveals that the provider is set via an environment variable, but it does not describe the return format, whether the image is saved or returned, file side effects, or error/ failure behavior. This leaves an agent with significant uncertainty about post-call outcomes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences lead with the action and then convey the critical environment-variable provider configuration. No filler or redundant restatement of the tool name is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose and provider configuration, and the schema covers all parameters. However, with no output schema, it should clarify what the agent receives after generation (e.g., a file path, URL, or binary) and any important side effects such as persistent file writes. These gaps make it only partially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the high-coverage baseline applies. The description adds no parameter-level detail beyond what the schema already provides, meriting neither penalty nor bonus.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb and resource ('Generate an image using AI models') and mentions multiple providers. Since there are no sibling tools and no differentiation is needed, it does not reach the 5-level distinction criterion, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit alternatives or when/ when-not conditions are provided, but the description implies the tool is the image-generation entry point. The provider configuration note is useful context but does not explain when to select one provider over another.

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. Dates show when Glama detected each change.

1 tool updatev1.0.2Aug 30, 2026
- First observedgenerate_image

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0

Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The single tool's purpose is clear and distinct.

Naming Consistency5/5

The only tool uses a clear verb_noun pattern (generate_image), and since there are no other tools, the naming is internally consistent.

Tool Count3/5

A single tool is borderline thin for a server even with a narrow purpose like image generation. While it covers the core action, agents might expect additional utilities such as provider listing or status checks.

Completeness4/5

The tool covers the primary domain action—generating an image—with support for multiple providers via configuration. Minor gaps exist, such as no way to query available models or provider details, but core generation is fully addressed.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp A
com.budgetpixel
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
AI & Machine Learning Image & Video Processing Audio Processing
1212
Claude Imagine AOAuth
com.claudeimagine
Generate AI images and videos from any compatible MCP client.
AI & Machine Learning Image & Video Processing
82
Writingmate MCPOAuth
ai.writingmate
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
AI & Machine Learning Image & Video Processing
1
mcp-qwen-imageOAuth
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1

Related MCP Servers

KOF Nano Banana MCP Server
Image & Video Processing Autonomous Agents Developer Tools
keeponfirst
A
license
A
quality
C
maintenance
Enables image generation using Gemini native models, supporting both single prompts and batch processing via a file-based queue. It allows for detailed configuration of aspect ratios and models using YAML frontmatter across various MCP-enabled clients.
Updated 7 months ago (2026-02-09 07:51 UTC)
3
19
MIT
Gemini Image MCP
Image & Video Processing Multimedia Processing Autonomous Agents
jk7g14
F
license
B
quality
D
maintenance
Enables image generation and multi-turn editing sessions using the Gemini API within MCP-compatible environments. Users can create, modify, and configure images through natural language commands, supporting features like aspect ratio adjustments and session-based image transformations.
Updated 7 months ago (2026-02-09 01:53 UTC)
5
-
Gemini Image Gen MCP Server
Image & Video Processing AI & Machine Learning
kevinten-ai
A
license
A
quality
C
maintenance
Enables AI image generation, editing, and upscaling via Google Gemini and Imagen models, supporting dynamic model switching and multiple MCP-compatible clients.
Updated a month ago (2026-08-10 16:38 UTC)
1
2
MIT
Image Generator MCP Server
AI & Machine Learning Image & Video Processing
ShushannaKarapetyan
F
license
Not graded
quality
C
maintenance
Enables MCP-compatible clients like Claude or ChatGPT to generate images from text prompts using AI, with options for aspect ratio and quality.
Updated 3 months ago (2026-06-18 09:15 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/genoooool/mcp-image-generator'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

@genoooool/mcp-image-generator

Features

Supported MCP Clients

Installation

Option 1: NPX (Recommended - No installation required)

Option 2: Global Install

Option 3: Local Install

Configuration

Environment Variables

How to Switch Provider

1. Using Yunwu Provider

2. Using Gemini Official Provider

3. Using Custom Gemini Provider

MCP Client Configuration

Claude Desktop

Configuration File Location

Configuration Format

Using Global Installation

Using Local Installation

Claude Code CLI

Configuration File Location

Configuration Format

Using Global Installation

Using Local Installation

OpenCode

Configuration File Location

Configuration Format

Codex

Configuration File Location

Configuration Format

Tool Usage

generate_image

Parameters

Return Value

Example Usage

Example 1: Generate a simple image

Example 2: Generate with custom filename

Example 3: Generate with direct URL (if supported)

Development

Build

Development Mode (with auto-reload)

Manual Testing

Provider Details

Yunwu Provider

Gemini Official Provider

Custom Gemini Provider

Error Handling

Troubleshooting

"IMAGE_PROVIDER environment variable is required"

"IMAGE_TOKEN is required when IMAGE_AUTH_TYPE=bearer"

"Unable to extract image from response"

Timeout errors

Claude Code doesn't show the MCP server

License

Author

Links

Available Tools

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

KOF Nano Banana MCP Server

Gemini Image MCP

Gemini Image Gen MCP Server

Image Generator MCP Server

Latest Blog Posts

MCP directory API

`generate_image`