I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

mcp
Model Context Protocol (MCP) server for Windsurf integration with image generation and web scraping capabilities.
3 years
Works with Finder
1
Github Watches
0
Github Forks
1
Github Stars
MCP Server for Windsurf/Roocode
This is a Model Context Protocol (MCP) server that provides image generation and web scraping capabilities for Windsurf.
Features
- Image Generation: Generate images using the Flux Pro model
- Web Scraping: Extract content from webpages using ScrapeGraph
Getting Started
-
Clone and set up the project:
git clone https://github.com/bananabit-dev/mcp.git cd mcp python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate pip install -r requirements.txt
-
Set up environment variables:
cp .env.example .env
Then edit
.env
to add your API keys:AIMLAPI_KEY=your_flux_pro_api_key SGAI_API_KEY=your_scrapegraph_api_key
MCP Server Configuration
- Add this configuration to
~/.codeium/windsurf/mcp_config.json
:
{
"mcpServers": {
"bananabit-mcp": {
"command": "/absolute/path/to/your/.venv/bin/python",
"args": ["-m", "app.mcp_server"],
"cwd": "/absolute/path/to/mcp",
"env": {
"PYTHONPATH": "/absolute/path/to/mcp",
"AIMLAPI_KEY": "${env:AIMLAPI_KEY}",
"SGAI_API_KEY": "${env:SGAI_API_KEY}"
}
}
}
}
- In Windsurf, click the hammer icon and "Refresh" to load the MCP server.
Example Usage
Image Generation
Let's create a cozy kawaii living room! Here's an example dialogue with Windsurf:
User: Generate a image of a cozy warm living room in kawaii and anime style.
Assistant: I'll help you generate a cozy warm living room image in kawaii and anime style!
[Generated image saved as cozy_kawaii_living_room.png]
User: Try again with an even more cozy and kawaii living room.
Assistant: I'll enhance the kawaii and cozy elements even more in this new version!
[Generated image saved as super_cozy_kawaii_living_room.png]
The MCP server will generate unique images each time, but they will follow the style and elements specified in the prompts. Try creating your own cozy spaces or other creative images!
Web Scraping
The MCP server provides powerful web scraping capabilities through the ScrapeGraph API. Here are the main features:
-
Content Extraction
# Extract main content from a webpage result = await extract_webpage_content( url="https://example.com" )
-
Markdown Conversion
# Convert webpage to clean markdown result = await markdownify_webpage( url="https://example.com", clean_level="medium" # Options: light, medium, aggressive )
-
Smart Scraping
# Extract specific information using AI result = await scrape_webpage( url="https://example.com" )
Features
- AI-Powered Extraction: Intelligently identifies and extracts main content
- Clean Output: Removes ads, navigation, and other clutter
- Format Options: Get content in raw HTML, markdown, or structured data
- Error Handling: Graceful fallbacks for failed extractions
- Customization: Control cleaning level and output format
Example Use Cases
-
Documentation Generation
# Create local documentation from online sources content = await markdownify_webpage( url="https://docs.example.com/guide", clean_level="medium" ) with open(".docs/guide.md", "w") as f: f.write(content)
-
Content Analysis
# Extract and analyze webpage sentiment content = await extract_webpage_content( url="https://example.com/article" ) sentiment = await analyze_text_sentiment( text=content["text"] )
-
Data Collection
# Extract structured data data = await scrape_webpage( url="https://example.com/products" ) # Process extracted data for item in data["structured_data"]: process_item(item)
Best Practices
-
Rate Limiting
- Respect website rate limits
- Add delays between requests
- Use caching when possible
-
Error Handling
try: content = await extract_webpage_content(url) except Exception as e: # Fall back to simpler extraction content = await markdownify_webpage(url)
-
Content Cleaning
- Start with "medium" clean_level
- Use "aggressive" for very noisy pages
- Use "light" when preserving format is important
-
Output Processing
- Validate extracted content
- Handle empty or partial results
- Process structured data appropriately
License
MIT
相关推荐
Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.
Confidential guide on numerology and astrology, based of GG33 Public information
A geek-themed horoscope generator blending Bitcoin prices, tech jargon, and astrological whimsy.
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Therapist adept at identifying core issues and offering practical advice with images.
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.
Mirror ofhttps://github.com/agentience/practices_mcp_server
Mirror ofhttps://github.com/bitrefill/bitrefill-mcp-server
Reviews

user_p7FoORMt
mcp has thoroughly impressed me with its seamless integration and robust functionality. As a dedicated user, I appreciate the thoughtfully designed features and the efficient user experience. Well-maintained by bananabit-dev, mcp stands as a testament to excellent software craftsmanship. Highly recommended for anyone seeking a reliable and user-friendly tool! For more details, visit the official GitHub repository: https://github.com/bananabit-dev/mcp.