Kafka MCP Server
An MCP server implementation for Kafka, allowing LLMs to interact with and manage Kafka clusters.
Features
- Cluster Management: View broker details
describe_cluster,describe_brokers. - Topic Management: List
list_topics, createcreate_topic, deletedelete_topic, describedescribe_topic, and increase partitionscreate_partitions. - Configuration Management: View
describe_configsand modifyalter_configsdynamic configs for topics, brokers, and groups. - Consumer Groups: List
list_consumer_groups, describedescribe_consumer_group, and securely manage offsets withreset_consumer_group_offsetandrewind_consumer_group_offset_by_timestamp. Advanced tools include state validation, dry runs, and execution audit logging. - Messaging: Consume messages
consume_messages(from beginning, latest, or specific offsets) and produce messagesproduce_message.
Prerequisites
- Python 3.10+
uvpackage manager (recommended)- A running Kafka cluster (e.g., local Docker, Confluent Cloud, etc.)
Installation
- Clone the repository.
- Install dependencies:
uv sync
