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., "@Symbol Image Generation MCP Server generate a 3D isometric claymorphic rocket symbol"
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 that exposes a tool for generating beautiful, stylized 3D claymorphic/glassmorphic symbol images (such as rockets, padlocks, badges) and automatically removing their background via the remove.bg API.
Exposes the generate_symbol_image tool to MCP clients (like Claude Desktop).
Auto-constructs a custom 3D isometric claymorphic/glassmorphic prompt matching your corporate UI aesthetics.
Dynamically generates images using Google AI Studio (Imagen 3), Stability AI (SD3/Ultra), or OpenAI (DALL-E 3) based on configured API keys.
Transparently removes background using the remove.bg API.
Saves the final high-fidelity transparent PNG.
Related MCP server: jgkme/kilo-image-gen-mcp
Node.js v18 or newer.
Navigate to the server folder:
cd c:/Users/Tateo/my-project/symbol-image-mcpInstall dependencies:
npm installThe server reads API keys from environment variables. Set at least one image generation API key (Google Imagen is preferred and checked first):
Variable | Description | Required |
| Google AI Studio API key (Imagen 3) | Yes (if using Google Imagen) |
| Stability AI API key | Yes (if using Stability AI) |
| OpenAI API key | Yes (if using OpenAI DALL-E) |
| remove.bg API key | Optional (defaults to |
To add this server to your Claude Desktop client, edit your configuration file located at:
%APPDATA%\Claude\claude_desktop_config.json
Add the server to the mcpServers object:
{
"mcpServers": {
"symbol-image-mcp": {
"command": "node",
"args": ["c:/Users/Tateo/my-project/symbol-image-mcp/index.js"],
"env": {
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE",
"STABILITY_API_KEY": "YOUR_STABILITY_API_KEY_HERE",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE"
}
}
}
}Restart Claude Desktop after updating the configuration.
You can start the server locally in stdio transport mode:
node index.jsThe server will start listening for JSON-RPC messages on standard input/output.
Generates a 3D claymorphic/glassmorphic symbol image, removes its background, and saves it.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The description of the object(s) to generate (e.g., 'a secure padlock, a stylized money bag with a won sign, and transaction card models') | |
| outputPath | No | Optional absolute path to save the final transparent PNG. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It mentions generating, background removal, and saving, but does not disclose any side effects, authorization needs, resource constraints, or what happens if outputPath is omitted. The lack of detail limits transparency.
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 sentence that front-loads the main action, but it omits important context (e.g., output format, fallback behavior). It is concise but at the cost of completeness.
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 complexity of image generation and processing, and no output schema, the description lacks details about the output format, size, quality, or any limitations. It provides minimal context for an AI agent to understand the full scope of the tool.
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 coverage is 100% with descriptions for both parameters. The description adds no new meaning beyond the schema, so a baseline score of 3 is appropriate.
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 (generates, removes, saves) and the resource (symbol image) with specific style (claymorphic/glassmorphic). It is unambiguous and distinct, though 'symbol image' could be more precise.
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. Since there are no sibling tools, it is assumed the only option, but no context for appropriate use cases or prerequisites is provided.
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.
v1.0.0generate_symbol_imageScored across 1 tool
With only one tool, there is no possibility of ambiguity. The agent will always choose the correct tool.
The single tool follows a clear verb_noun pattern (generate_symbol_image), establishing a consistent and descriptive naming style.
One tool is appropriate for a focused server dedicated to generating a specific type of symbol image. It covers the core functionality without unnecessary bloat.
The tool covers the primary task of generating, removing background, and saving a symbol image. However, it may lack options for different styles or customizations, leaving minor gaps for advanced use cases.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
MCP server for Qwen Image 3 AI image generation
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
Generate AI images and videos from any compatible MCP client.
