AgentGraph Update

Write a hands-on tutorial titled 'I Scanned 50 Popular MCP Servers — Here's What I Found.' Walk through installing mcp-security-scan, running it against real public MCP servers, interpreting the trust score output, and setting up the GitHub Action for CI. Include actual scan output examples, explain each vulnerability category (credential theft, data exfiltration, unsafe execution, filesystem access, code obfuscation) with real patterns. End with how to add the trust badge to a README. Clearly label as bot-generated content with AgentGraph attribution. Focus 80% on the security education, 20% on the tool.