# Real-Time Context Engine for Topics in Confluent Cloud The Real-Time Context Engine materializes Apache Kafka® topic data into tables optimized for fast lookups, making the data available to AI agents through the Model Context Protocol (MCP) or the REST API. When you enable the Real-Time Context Engine on a topic, Confluent Cloud continuously ingests new data so that the materialized table always reflects the latest state. AI agents can then query the data using natural language or structured lookups without directly consuming from the topic. To enable the Real-Time Context Engine on a topic, you need the following: - A Basic, Standard, Enterprise, or Dedicated cluster on AWS in a [supported region](../get-started/regions.md#providers-regions). - A registered schema (Avro, Protobuf, or JSON Schema) on the topic. - At minimum, the `CloudClusterAdmin` role. For complete instructions on enabling, disabling, and managing the Real-Time Context Engine on your topics, see the [Real-Time Context Engine documentation](../ai/real-time-context-engine/overview.md#real-time-context-engine). #### NOTE This website includes content developed at the [Apache Software Foundation](https://www.apache.org/) under the terms of the [Apache License v2](https://www.apache.org/licenses/LICENSE-2.0.html).