Uses Cheerio for web scraping and HTML parsing to extract structured content from web pages
Provides Docker containerization and deployment capabilities for the MCP server with Docker Compose support
Enables direct installation from GitHub repositories and distribution of the MCP server package
Built on the Hono web framework to provide ultra-fast HTTP server capabilities and API endpoints
Runs on Node.js runtime environment with TypeScript support for server operations
Provides npm package management for installation, dependency management, and global command-line tool distribution
Implements type-safe operations and development using TypeScript with comprehensive type checking
Uses Zod for runtime schema validation and type safety across all data operations and API inputs
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., "@MCP Content Analyzer analyze this webpage about AI trends and save it to the database"
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 fast MCP (Model Context Protocol) server that enables Claude to scrape websites, process documents (PDF, DOCX, TXT), and manage Excel databases.
One command installs everything:
curl -fsSL https://raw.githubusercontent.com/DuncanDam/my-mcp/main/install.sh | bashThen run:
my-mcp setup # Setup configuration
my-mcp config # Configure Claude Desktop
# Restart Claude Desktop completely (MCP server starts automatically)Related MCP server: Hyperbrowser MCP Server
Automatic update (recommended):
my-mcp updateManual update:
curl -fsSL https://raw.githubusercontent.com/DuncanDam/my-mcp/main/install.sh | bashWorkflows (Recommended):
analyze_content_workflow - Complete content analysis pipeline
scrape_and_save_content - Web scraping with Excel integration
Individual Tools:
scrape_webpage - Extract content from URLs
read_document - Process PDF, DOCX, TXT, RTF files
add_content_entry - Save content to Excel database
search_similar_content - Find related content
test_connection - Test MCP connectivity
Command | Description |
| Install dependencies and setup |
| Configure Claude Desktop |
| Start server (development/testing only) |
| Test server connection |
| Development mode |
| Show all commands |
Web content:
Use analyze_content_workflow to process https://example.com with topic "News"Document:
Use analyze_content_workflow to process /path/to/document.pdf with topic "Research"Screenshot: Share image with Claude, then:
Use analyze_content_workflow with the text you extracted, sourceDescription "Meeting notes", and topic "Business"If the script fails:
git clone https://github.com/DuncanDam/my-mcp.git
cd my-mcp
npm install && npm run build && npm install -g .
my-mcp setup && my-mcp config
# Restart Claude DesktopTest connection: my-mcp test
Check logs: tail -f ~/Library/Logs/Claude/mcp-server-*.log
Reinstall: Run the installation command again
Permission issues: sudo npm install -g . (macOS/Linux)
Your system works if:
my-mcp test shows "✅ MCP server is responding"
Claude can call test_connection
Web scraping and document processing work in Claude
Ready to use! After Claude Desktop restart, test the connection in Claude Desktop.
This server cannot be deployed
8-tool AI web intelligence suite: search, scrape, screenshot, SEO, docs, crypto, code.
Web scraping, code review, content gen, sentiment. Zero Core Tools.
One key for the document-to-web pipeline: scrape, AI-extract, build & edit PDFs, fill forms.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
