MCP Server logo

MCP Server

by bananabit-dev

The MCP Server provides image generation and web scraping capabilities. It is designed to work with Windsurf, enabling users to generate images using the Flux Pro model and extract content from webpages using ScrapeGraph.

View on GitHub

Last updated: N/A

What is MCP Server?

The MCP Server is a Model Context Protocol server that integrates image generation (using Flux Pro) and web scraping (using ScrapeGraph) functionalities, primarily designed for use with the Windsurf application.

How to use MCP Server?

To use the MCP Server, first clone the repository and set up the environment by installing dependencies and configuring API keys. Then, configure Windsurf to connect to the MCP server by adding the server configuration to ~/.codeium/windsurf/mcp_config.json. Finally, refresh Windsurf to load the MCP server.

Key features of MCP Server

  • Image Generation using Flux Pro

  • Web Scraping using ScrapeGraph

  • AI-Powered Content Extraction

  • Markdown Conversion of Webpages

Use cases of MCP Server

  • Generating images based on text prompts within Windsurf

  • Extracting content from webpages for documentation generation

  • Analyzing webpage sentiment by extracting content and using sentiment analysis tools

  • Collecting structured data from websites for data processing

FAQ from MCP Server

How do I set up the MCP server?

Clone the repository, install dependencies, configure API keys in .env, and add the server configuration to Windsurf's mcp_config.json.

What is Flux Pro?

Flux Pro is the image generation model used by the MCP server.

What is ScrapeGraph?

ScrapeGraph is the web scraping API used by the MCP server to extract content from webpages.

How do I generate images?

Use the appropriate prompts in Windsurf to request image generation. The MCP server will generate images based on your prompts.

How do I perform web scraping?

Use the provided Python code snippets to extract content from webpages using ScrapeGraph's functions like extract_webpage_content, markdownify_webpage, and scrape_webpage.