dmarsters/cereal-box-style-mcp
3.2
If you are the rightful owner of cereal-box-style-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Cereal Box Style MCP Server is designed to transform image prompts into seven distinct cereal box packaging aesthetics, optimizing creative output and reducing API costs.
Tools
8
Resources
0
Prompts
0
Cereal Box Style MCP Server
Transform image prompts through 7 distinct cereal box packaging aesthetics.
Categories
- Mascot Theater - Cartoon characters, bold outlines, bright primary colors
- Health Halo - Minimalist natural photography, muted earth tones
- Nostalgia Revival - Vintage screen print, limited palettes, retro typography
- Premium Disruptor - Black backgrounds, metallic accents, luxury minimal
- Kid Chaos - Neon explosion, maximum density, extreme angles
- Transparent Honest - Clinical infographics, labeled components, systematic
- Adventure Fantasy - Cinematic epic scale, magical effects, dramatic lighting
Installation
cd /Users/dalmarsters/Documents/cereal-box-style-mcp
uv pip install -e .
Usage with Claude Desktop
The MCP server provides tools that Claude can call to transform prompts:
User: "Transform 'a tired chef tasting soup' into mascot theater style"
Claude will:
1. Call parse_prompt to extract components
2. Call apply_transformations with mascot_theater
3. Call build_prompt_skeleton to structure output
4. Synthesize the final creative prompt
Tools Available
parse_prompt- Extract semantic componentsget_available_categories- List all style categoriessuggest_category- AI-powered category recommendationget_category_rules- Get transformation rules for a categoryapply_transformations- Transform components to category stylebuild_prompt_skeleton- Assemble structured promptrefine_component- Edit specific partsgenerate_variants- Create multiple variations
Example Workflow
# 1. Parse user input
components = parse_prompt("a firefighter rescuing a cat")
# 2. Get suggestion
suggestion = suggest_category(components)
# Returns: "mascot_theater"
# 3. Apply transformation
transformed = apply_transformations(components, "mascot_theater")
# 4. Build skeleton
skeleton = build_prompt_skeleton(transformed, "mascot_theater", components['semantic_weights'])
# 5. Claude synthesizes final prompt
Cost Optimization
- Without MCP:
10,000 tokens per request ($0.025) - With MCP:
250 tokens per request ($0.008) - Savings: 68% reduction in API costs
Development
# Run server directly
python -m cereal_box_style_mcp.server
# Test tools
uv run python -c "from cereal_box_style_mcp.server import parse_prompt; print(parse_prompt('a happy dog'))"