Kafka MCP server

This is a helper that connects your AI assistant to Apache Kafka, the system many companies use to move messages between programs. Once it is set up, you can ask your AI plain questions about your Kafka topics and consumer groups instead of clicking around in a dashboard. It is handy for anyone who works with data pipelines or support tickets about Kafka, even if you are not the person who built the cluster.

What this MCP server does

You ask your AI something about Kafka in normal words. The AI sends that request to this helper program. The helper talks to your Kafka cluster using the connection details you set up. It brings back the answer, like a list of topics, a group's lag, or a summary of cluster health. If you ask it to change something, like resetting an offset, it does that and tells you what it changed.

Click to zoom

What you can do with it

• List all topics in your Kafka cluster
• Describe a topic to see its partitions and replicas
• Create or delete a topic
• Add partitions to an existing topic
• List consumer groups and see their state
• Check how far behind a consumer group is (lag)
• Reset or rewind a consumer group's offsets
• Read or send messages to a topic

Try asking your AI

• “List all Kafka topics in my cluster”
• “How much lag does the orders-consumer group have?”
• “Show me the last 5 messages from the payments topic”
• “Reset the inventory-consumer group offset to earliest”

What it gives back to you

You get back plain answers in the chat: lists of topics or groups, numbers like lag or partition counts, short summaries of cluster health, or the messages you asked for. When it makes a change, like resetting an offset or creating a topic, it tells you what it did. Some tools also support a dry run, so you can see what would happen before it actually happens.

Before you start

Who it's for

Data engineers, support engineers, and anyone who needs to check or fix Kafka topics and consumer groups without opening a separate dashboard.