The main concern I have is that there's not a well defined security context in any agentic system. They are assumed to be "good" but that's not good enough.
Good article, Edoardo! The ideas about securing MCP frameworks with servlets are really interesting. Just added your article to https://github.com/Puliczek/awesome-mcp-security
https://docs.mcp.run/blog/2025/04/07/mcp-run-security