The EverArt Forge MCP Server integrates with EverArt's AI models to generate and manage images for web development projects.
Generate Images:
Create SVG vector graphics using Recraft-Vector model, ideal for logos and icons
Produce raster images (PNG, JPEG, WebP) with various AI models (FLUX1.1, FLUX1.1-ultra, SD3.5, Recraft-Real)
Generate multiple images simultaneously (up to 10)
Specify detailed text prompts for customized image content
Manage Images:
List all previously generated images stored by the server
View specific images in your system's default image viewer
Save to custom paths or web project directories
Seamless integration with various project types (React, Vue, Next.js)
Customize Output:
Control model selection, format, output path, image count, and other parameters
Ensure proper asset organization and responsive formats for web integration
Click on "Install 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., "@EverArt Forge MCP Server generate a minimalist tech logo in SVG format using the Recraft-Vector model"
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.
An advanced Model Context Protocol (MCP) server for Cline that integrates with EverArt's AI models to generate both vector and raster images. This server provides powerful image generation capabilities with flexible storage options and format conversion.
Vector Graphics Generation
Create SVG vector graphics using Recraft-Vector model
Automatic SVG optimization
Perfect for logos, icons, and scalable graphics
Raster Image Generation
Support for PNG, JPEG, and WebP formats
Multiple AI models for different styles
High-quality image processing
Flexible Storage
Custom output paths and filenames
Automatic directory creation
Format validation and extension handling
Web project integration
Related MCP server: Gemini Image MCP
5000:FLUX1.1: Standard quality, general-purpose image generation
9000:FLUX1.1-ultra: Ultra high quality for detailed images
6000:SD3.5: Stable Diffusion 3.5 for diverse styles
7000:Recraft-Real: Photorealistic style
8000:Recraft-Vector: Vector art style (SVG output)
Clone the repository:
git clone https://github.com/nickbaumann98/everart-forge-mcp.git
cd everart-forge-mcpInstall dependencies:
npm installBuild the project:
npm run buildGet your EverArt API key:
Sign up at EverArt
Navigate to your account settings
Create or copy your API key
Add the server to your Cline MCP settings file:
For VS Code Extension:
Edit ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:
{
"mcpServers": {
"everart-forge": {
"command": "node",
"args": ["/absolute/path/to/everart-forge-mcp/build/index.js"],
"env": {
"EVERART_API_KEY": "your_api_key_here"
},
"disabled": false,
"autoApprove": []
}
}
}For Claude Desktop App:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or appropriate location for your OS
Restart Cline to load the new MCP server
Once configured, you can use Cline to generate images with prompts like:
"Generate a minimalist tech logo in SVG format using the Recraft-Vector model"
"Create a photorealistic landscape image with the FLUX1.1-ultra model"
"Make me a vector icon for my project that represents artificial intelligence"
"Generate a professional company logo as an SVG file and save it to my desktop"
The server provides these tools:
Generate images with extensive customization options:
Parameters:
- prompt (required): Text description of desired image
- model: Model ID (5000:FLUX1.1, 9000:FLUX1.1-ultra, 6000:SD3.5, 7000:Recraft-Real, 8000:Recraft-Vector)
- format: Output format (svg, png, jpg, webp)
- output_path: Custom output path for the image
- web_project_path: Path to web project root for proper asset organization
- project_type: Web project type (react, vue, html, next, etc.)
- asset_path: Subdirectory within the web project assets
- image_count: Number of images to generate (1-10)Notes:
SVG format is only available with Recraft-Vector (8000) model
Default format is "svg" for model 8000, "png" for others
You can specify combined model IDs (e.g., "8000:Recraft-Vector")
List all previously generated images stored by the server.
Open a specific image in the default image viewer:
Parameters:
- filename: Name of the image file to viewError: Invalid model ID: Make sure you're using one of the supported model IDs (5000, 6000, 7000, 8000, 9000)
Format not compatible with model: SVG format is only available with Recraft-Vector (8000) model
Image not found: Use the list_images tool to see available images
API authentication failed: Check your EverArt API key
Images not appearing: Check file permissions and paths
MIT License - see LICENSE file for details.
Generate images using EverArt Models, optimized for web development. Supports web project paths, responsive formats, and inline preview. Available models:
5000:FLUX1.1: Standard quality
9000:FLUX1.1-ultra: Ultra high quality
6000:SD3.5: Stable Diffusion 3.5
7000:Recraft-Real: Photorealistic style
8000:Recraft-Vector: Vector art style (SVG format)
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text description of desired image | |
| model | No | Model ID (5000:FLUX1.1, 9000:FLUX1.1-ultra, 6000:SD3.5, 7000:Recraft-Real, 8000:Recraft-Vector) | 5000 |
| format | No | Output format (svg, png, jpg, webp). Note: Vector format (svg) is only available with Recraft-Vector (8000) model. | svg |
| output_path | No | Optional: Custom output path for the generated image. If not provided, image will be saved in the default storage directory. | |
| web_project_path | No | Path to web project root folder for storing images in appropriate asset directories. | |
| project_type | No | Web project type to determine appropriate asset directory structure (e.g., 'react', 'vue', 'html', 'next'). | |
| asset_path | No | Optional subdirectory within the web project's asset structure for storing generated images. | |
| image_count | No | Number of images to generate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It lists available models and hints at web project integration but fails to describe critical behaviors like authentication needs, rate limits, error handling, or what happens when images are generated (e.g., saved to disk, returned as data). For a complex 8-parameter tool with no annotation coverage, this is a significant gap.
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 efficiently structured with a clear opening sentence and a bulleted list of models. However, the model list could be more concise (e.g., by grouping similar models), and some sentences like 'Supports web project paths, responsive formats, and inline preview' are vague and could be tightened.
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 tool's complexity (8 parameters, no annotations, no output schema), the description is incomplete. It lacks details on return values (e.g., image URLs, file paths), error conditions, web development integration specifics, and behavioral constraints. For a generative tool with multiple parameters, this leaves significant gaps for an AI agent.
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 schema already documents all 8 parameters thoroughly. The description adds some value by listing model options with quality/style notes, but it doesn't provide additional semantic context beyond what's in the schema (e.g., explaining 'web_project_path' integration or 'project_type' implications). Baseline 3 is appropriate when the schema does the heavy lifting.
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 generates images using EverArt Models and specifies it's optimized for web development, which provides a specific verb+resource. However, it doesn't explicitly distinguish this from sibling tools like 'list_images' or 'view_image' beyond the core generation function, preventing a perfect score.
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 provides no guidance on when to use this tool versus alternatives like 'list_images' or 'view_image'. It mentions web development optimization but doesn't specify scenarios where this is preferred over other image-related tools or when not to use it, leaving usage context implied at best.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all stored images
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('List all stored images') but doesn't describe what 'List' entails—such as whether it returns metadata, thumbnails, or full images; if there's pagination or filtering; or any performance or rate-limiting considerations. This leaves significant gaps in understanding the tool's 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?
The description 'List all stored images' is extremely concise—a single, clear sentence with no wasted words. It's front-loaded and efficiently communicates the core action without any fluff, making it easy for an agent to parse quickly.
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 tool's simplicity (0 parameters, no output schema, no annotations), the description is minimal but insufficient. It doesn't explain what 'List' returns (e.g., a list of image IDs, metadata, or URLs), which is critical for a tool with no output schema. For a basic list operation, more context on the return format is needed to be complete.
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 0 parameters with 100% coverage, so the schema fully documents the lack of inputs. The description doesn't add parameter details beyond this, but since there are no parameters to explain, it doesn't need to compensate. A baseline of 4 is appropriate as the description doesn't contradict or add unnecessary information.
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 'List all stored images' clearly states the verb ('List') and resource ('stored images'), making the tool's purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'view_image' (which might show a single image) or 'generate_image' (which creates new images), so it doesn't reach the highest score.
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 provides no guidance on when to use this tool versus alternatives like 'view_image' or 'generate_image'. It doesn't mention any prerequisites, exclusions, or contextual factors that would help an agent choose between these tools, leaving the usage unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open a stored image in the default image viewer
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | Name of the image file to view |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool opens an image in a viewer, implying a read-only operation, but lacks details on behavioral traits such as whether it requires specific permissions, if it launches an external application, or any error handling (e.g., if the file doesn't exist). This leaves gaps for safe agent invocation.
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 directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly.
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 tool's simplicity (one parameter, no output schema), the description is minimal but incomplete. It lacks context on usage guidelines, behavioral transparency (e.g., what happens if the file is missing), and doesn't leverage the absence of annotations to compensate, making it inadequate for safe agent operation.
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 description adds no parameter semantics beyond the input schema, which has 100% coverage and fully documents the single 'filename' parameter. This meets the baseline of 3, as the schema handles the heavy lifting, but the description doesn't provide additional context like file format support or path specifications.
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 ('Open') and resource ('stored image'), specifying it opens in the default image viewer. However, it doesn't explicitly differentiate from sibling tools like 'generate_image' (creates new images) or 'list_images' (lists existing images), which is a minor gap.
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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., the image must already exist), exclusions, or comparisons to sibling tools like 'generate_image' for creating images or 'list_images' for browsing available images.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The three tools have clearly distinct purposes: generate_image creates new images, list_images enumerates stored images, and view_image opens a specific stored image. There is no overlap or ambiguity between these functions, making it easy for an agent to select the correct tool for each task.
All tool names follow a consistent verb_noun pattern with snake_case: generate_image, list_images, and view_image. This predictable naming scheme enhances readability and usability, with no deviations or mixed conventions.
With only three tools, the server feels thin for an image generation and management domain. While the tools cover basic operations (create, list, view), more advanced functionality like editing, deleting, or organizing images is missing, which could limit agent workflows in practice.
The tool surface is significantly incomplete for an image management server. There are notable gaps: no ability to delete, update, or organize images (e.g., tagging, moving), and no tools for managing the generation process (e.g., canceling jobs, checking status). This will likely cause agent failures when trying to perform common image-related tasks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Qwen Image 3 AI image generation
MCP server for Flux AI image generation
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
MCP server for NanoBanana AI image generation and editing
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nickbaumann98/everart-forge-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
