Delight.ai, the industry’s first branded AI concierge built for customer experience, announced Delight Agent Model Context Protocol (MCP), giving customers the ability to ask external AI assistants questions about live data from their Delight.ai workspace using natural language.
Earlier this year, Delight.ai introduced MCP Tool Import, enabling customers to consume their own MCP servers as tools with Delight.ai agents. The Delight Agent MCP works in the opposite direction: Delight.ai now publishes its own MCP, allowing external AI clients to securely access and query live data from a customer’s Delight.ai workspace.
With Delight Agent MCP, teams can ask AI assistants such as 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 rather than relying on standard dashboards or exported reports. The announcement reflects a broader industry shift toward AI assistants that can securely interact with enterprise applications directly, which gives users the ability to retrieve information and complete tasks through natural language instead of navigating multiple interfaces.
Also Read: BigID Defines the Missing Governance Layer for Autonomous AI Agents
“Enterprise software is becoming something you talk to, not something you log into,” said John Kim, CEO and co-founder of Delight.ai, a Sendbird company. “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.”
The new capability gives organizations direct access to more than 35 operational tools from launch, including:
- Monitor agent performance: Check resolution rate, CSAT 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
The Delight Agent MCP was developed using Delight.ai’s own internal workflows before becoming generally available and was further shaped by customer demand for direct, standards-based access to live operational data without requiring export workflows.
SOURCE: PRNewswire