Real-Time Context Engine in Confluent Cloud
The Real-Time Context Engine is the Model Context Protocol (MCP) interface to Lightning Tables in Confluent Intelligence. You enable a Lightning Table for an Apache Kafka® topic, and your AI agents query its most current data through the Real-Time Context Engine.
Demo: Querying a topic for live data
In this demo, you ask Claude Code questions about a live logistics fleet in natural language. Claude Code connects to the Real-Time Context Engine through MCP. It discovers the available topics, inspects their schemas, and queries the latest data to answer each question. For example, you ask which driver is on an active route and whether any fragile packages are in transit. Because the Real-Time Context Engine serves the most current state of each Kafka topic, the answers reflect live data.
Get started with the Real-Time Context Engine
To give an AI agent real-time context from your topics, complete the following steps:
Enable a Lightning Table on each topic that the agent needs. For the steps, see Enable a Lightning Table for a topic.
Connect the agent to the Real-Time Context Engine through an MCP client. For the steps, see Query a Lightning Table with MCP in Confluent Cloud.
For a complete walkthrough, see Get Started with Lightning Tables in Confluent Cloud.
Relationship to other Confluent MCP servers
The Real-Time Context Engine exposes data to AI agents through an MCP server that focuses on delivering real-time business data from your Kafka topics. Confluent also provides other MCP servers for a different purpose: letting AI assistants manage Confluent resources like environments, clusters, topics, and connectors.
The two are complementary. Use the other Confluent MCP servers to set up and monitor your Confluent Cloud infrastructure, and the Real-Time Context Engine to connect your AI applications to the data flowing through that infrastructure.