Delight.ai, providers of a branded artificial intelligence concierge for customer experience, today launched Delight Agent Model Context Protocol (MCP), enabling customers to ask external AI assistants questions about live data from their Delight.ai workspace using natural language.
With Delight Agent MCP, teams can ask AI assistants like Claude, Codex, and Cursor questions including, "Why did customer satisfaction drop this week?" or "How's my agent doing today?" and receive answers backed by operational data.
The new capability gives organizations direct access to more than 35 operational tools, including the following:
- Resolution rate, customer satisfaction, and category breakdowns.
- Search conversations: Search and read full conversation transcripts.
- Quality monitoring: Identify low-confidence responses, safeguard flags, and user feedback.
- Write operations: Create and update actionbooks, tools, knowledge sources, and agent configuration.
"Enterprise software is becoming something you talk to, not something you log into," said John Kim, CEO and co-founder of Delight.ai, in a statement. "Instead of opening dashboards, exporting data and piecing together answers, teams should be able to ask a question and receive an answer grounded in operational data. That's where AI-powered work is headed."