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 Image Generator Generate a Ghibli-style image of a cat sleeping 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.
A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Generate high-quality images from text prompts
Support for multiple anime and artistic styles:
Ghibli Style
Pixar Style
Pokemon Style
Genshin Impact Style
Cyberpunk Style
One Piece Style
Attack on Titan Style
Shinkai Makoto Style
Sailor Moon Style
Evangelion Style
Disney Princess Style
Kyoto Animation Style
Dreamworks Animation Style
Marvel Studios Style
DC Comics Style
Kawaii Pastel Style
Simpsons Style
Dragon Ball Style
Demon Slayer Style
Warner Bros Animation Style
Dark Fantasy Style
And many more Japanese anime styles
Multiple image size options:
Square (512x512)
Square HD (1024x1024)
Portrait 4:3 (768x1024)
Portrait 16:9 (576x1024)
Landscape 4:3 (1024x768)
Landscape 16:9 (1024x576)
Generate multiple images in one request (up to 4)
Image upscaling (4x resolution enhancement)
Image search and replace functionality
Built-in NSFW content detection
Related MCP server: fal-mcp
Clone the repository:
git clone [repository-url]
cd aiimagemultistyleInstall dependencies:
npm installConfigure environment variables:
Create a .env file with the following content:
FALAI_API_KEY=your_fal_ai_key_hereTo use the MCP Image Generator server, add it to your mcpServers configuration:
{
"mcpServers": {
"image-generator": {
"command": "npx",
"args": ["-y", "aiimagemultistyle"]
}
}
}You can also specify additional configuration options:
{
"mcpServers": {
"image-generator": {
"command": "npx",
"args": [
"-y",
"aiimagemultistyle",
"--mode=rest",
"--port=9593",
"--endpoint=/rest"
],
"env": {
"FALAI_API_KEY": "your_fal_ai_key_here"
}
}
}
}The server can run in two modes:
STDIO mode (default):
npm startREST mode:
npm start -- --mode=rest --port=9593 --endpoint=/restRequest Format:
{
"name": "generate_image",
"arguments": {
"prompt": "A beautiful sunset over mountains",
"style": "ghibli-style",
"num_images": 1,
"size": "square_hd"
}
}Parameters:
prompt (required): Text description of the image to generate
style (optional): Image style (default: "ghibli-style")
Available styles: See the Features section above for the complete list
num_images (optional): Number of images to generate (1-4, default: 1)
size (optional): Image size (default: "square_hd")
Available sizes: "square", "square_hd", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9"
Request Format:
{
"name": "upscale_image",
"arguments": {
"image_url": "https://example.com/image.jpg"
}
}Parameters:
image_url (required): URL of the image to upscale
Request Format:
{
"name": "search-and-replace",
"arguments": {
"image_url": "https://example.com/image.jpg",
"mask_url": "https://example.com/mask.jpg",
"prompt": "Description of the replacement"
}
}Parameters:
image_url (required): URL of the image to edit
mask_url (required): URL of the mask image (black areas preserved, white areas inpainted)
prompt (required): Description of the replacement content
npm run build: Build the project
npm run watch: Watch mode for development
npm run inspector: Run MCP inspector
The server provides detailed error messages for common issues:
Missing API key
Invalid prompt
Invalid style or size parameters
API request failures
NSFW content detection
MIT
Generate images using fal.ai with various styles and options.
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Image size | square_hd |
| style | No | Image style | ghibli-style |
| prompt | Yes | The prompt to generate the image from | |
| num_images | No | Number of images to generate (1-4) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only mentions generating images with styles and options, but does not disclose any behavioral traits such as generation time, costs, safety, or potential destructive actions.
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?
The description is a single, clear sentence that is front-loaded with purpose. It is concise, but could pack more useful detail without becoming verbose.
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?
The description is minimal for a generation tool with no output schema. It omits information about output type, generation time, rate limits, and differentiation from sibling tools. Given the tool's complexity and lack of annotations, more context is needed.
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?
Schema description coverage is 100%, with all parameters having descriptions. The tool description adds only a generic statement about 'various styles and options', providing little extra meaning beyond the schema. Baseline is 3.
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?
The description clearly states the verb 'generate' and resource 'images using fal.ai', with 'various styles and options' adding context. However, it does not differentiate from sibling tools like upscale_image, which also deals with images.
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?
No guidance on when to use this tool vs alternatives. There is no mention of context, prerequisites, or exclusions. The description lacks any usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Replace objects or elements in an image using text descriptions.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | The prompt to use for generating the image. Be as descriptive as possible for best results. | |
| mask_url | No | Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted. | |
| image_url | Yes | Input image for img2img or inpaint mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It describes a mutation (replacement) but does not detail whether the operation is destructive, how the rest of the image is handled, or what the output format is. The mention of 'inpaint mode' in the mask_url schema description is not echoed in the tool 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?
The description is a single, efficient sentence that conveys the core purpose without filler. However, it could benefit from additional context without becoming verbose, so slightly below perfect.
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?
Given the presence of three parameters with full schema descriptions and no output schema, the description is adequate but lacks information about expected output, behavior when using mask, or any side effects. It leaves some gaps for an agent to infer.
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?
Schema description coverage is 100%, so the baseline is 3. The tool description adds no additional meaning beyond what the schema already provides for each parameter (prompt, mask_url, image_url).
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?
The description clearly states the tool's purpose: 'Replace objects or elements in an image using text descriptions.' It identifies the verb (replace), resource (objects/elements in an image), and method (text descriptions), distinguishing it from sibling tools which generate or upscale images.
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?
The description implies usage for replacing objects, but does not provide explicit guidance on when to use this tool versus alternatives like generate_image or upscale_image, nor does it mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enhance image resolution by 4x using fal.ai upscaling.
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | The URL of the image to upscale |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only mentions the upscaling factor but does not disclose potential side effects, rate limits, output format, or whether the operation is destructive. This leaves the agent uninformed about behavior.
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?
Single sentence with no filler, very concise.
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?
The tool is simple with one parameter, but the description omits critical details such as what the output is (URL? base64?) and any limitations. With no output schema, the description should specify the return format to enable correct handling.
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?
The input schema has full coverage for the single parameter. The description adds no extra information about the parameter beyond the schema definition.
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?
The description clearly states the action (enhance), the resource (image), the scaling factor (4x), and the service (fal.ai). It distinguishes from siblings which are image generation and text replacement.
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?
No guidance on when to use this tool versus alternatives like generate_image. No mention of prerequisites or context like image URL must be valid.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0generate_imagesearch-and-replaceupscale_imageScored across 3 tools
Each tool targets a clearly distinct operation: generating new images, editing objects in existing images, and upscaling resolution. There is no overlap in purpose, so an agent can reliably distinguish them.
Two tools (generate_image, upscale_image) follow a consistent verb_noun pattern, but search-and-replace uses a hyphenated phrase, breaking the pattern. The inconsistency is minor and does not impede understanding.
With 3 tools, the server is borderline small for a comprehensive image service, but it covers core tasks (generation, editing, enhancement). The count feels slightly thin but not unreasonable.
The tools cover generation, editing, and upscaling, but lack common operations like cropping, resizing, or style transfer. The editing tool is limited to object replacement, leaving gaps for general image manipulation.
MCP server for Flux AI image generation
MCP server for NanoBanana AI image generation and editing
MCP server for Midjourney AI image generation and editing
MCP server for Qwen Image 3 AI image generation