George Gerchow:Building an MCP Sensitive Data Sentinel for AI Agents
Registration
About Event
AI agents can ingest or leak sensitive data through MCP servers. I show how to build a small MCP sentinel that scans requests and tool arguments, detects partial and transformed sensitive content, and blocks unsafe use with local audit trails. One clear example: a request moves from the clipboard to the agent, is intercepted, and is denied. Attendees take home code and a checklist to deploy quickly.