Enables MCP-compatible AI agents to execute typed live-app actions over WebSocket, allowing agents to directly interact with real application state without browser automation or scraping.
MCP server that exposes WebSocket session management as tools, allowing AI agents to open persistent connections, send typed frames, drain buffered messages, and monitor per-frame Shannon entropy to detect schema divergence.
Enables AI agents to interact with Dash dashboards by exposing them as MCP servers via a WebSocket bridge, with automatic tool registration and human-in-the-loop confirmation.