Web Content MCP
by hmalfee
The Web Content MCP server provides tools to search Google and scrape data from the top results, or directly visit and scrape content from provided URLs. It's designed for fast and efficient web content retrieval.
Last updated: N/A
What is Web Content MCP?
Web Content MCP is a server that provides two tools: web-search for scraping content from Google search results and url for directly scraping content from specified URLs.
How to use Web Content MCP?
To use, first clone the repository, install dependencies, and configure the .env file with your Google API key and search engine ID. Then, configure the server in Claude Desktop or VSCode using the provided JSON configurations. Finally, access the server in Claude prompts using the Search for information about [search query] or Visit and summarize information from [URL] commands.
Key features of Web Content MCP
Fast and efficient web content retrieval
Support for both search-based and direct URL access
Compatible with Claude Desktop, VSCode, and any agent that supports MCP servers
TypeScript support
Use cases of Web Content MCP
Automated content gathering for research
Summarizing web pages for quick information access
Integrating web scraping into AI agents
Data extraction for analysis
FAQ from Web Content MCP
What if I get connection errors?
What if I get connection errors?
Make sure the server is running and the path to your files is correct.
What if I get API errors?
What if I get API errors?
Verify that your API keys in the .env file are valid.
What if I have path issues?
What if I have path issues?
Double-check the paths in your configuration files.
What are the prerequisites for running this server?
What are the prerequisites for running this server?
You need Node.js, pnpm/npm, and TypeScript support installed. Also, you need a .env file with the required API keys.
How do I contribute to this project?
How do I contribute to this project?
Contributions are welcome! Please feel free to submit a Pull Request.