MCP server · Developer tools

Kafka MCP server

Debug Kafka with your AI: find messages, check consumer lag, and compare clusters.

Developer tools Analytics For it and development For operations Databases

This is a helper that lets your AI assistant work with Apache Kafka, the system many companies use to move messages between programs. It is meant for people who already have Kafka running and need to look into problems, like a message that never arrived or a consumer that stopped keeping up. You do not need to be a Kafka expert to use it, but you do need access to a Kafka cluster.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another system. This one connects your AI to Kafka, so it can look up messages, check how far behind a consumer is, and help you fix things when you ask. You set it up once, and after that you just talk to your AI in plain words.

What this MCP server does

You ask your AI a question about your Kafka data, like why a consumer is stuck. Your AI sends that request to this helper program running on your computer. The helper talks to your Kafka cluster using the connection details you gave it. It reads messages, measures lag, or makes a change if you allowed that. Then it sends the answer back to your AI, which explains it to you in the chat.

What you can do with it

Find messages by key or by a field inside the message
Measure consumer lag and see when it clears
Unblock a stuck consumer by committing its offset
Compare two Kafka clusters to spot differences
Copy a message from one cluster to another
Create a topic or produce a new message
Download a batch of messages to a file on your machine

Try asking your AI

“Find all messages on the orders topic with order id 12345”
“Why is the payments consumer group lagging so far behind?”
“Compare the prod and preprod clusters for the users topic”
“Copy that last message from prod to the preprod cluster”

What it gives back to you

You get answers in the chat: a list of matching messages, a lag number with a short explanation, a side by side comparison of two clusters, or a confirmation that a change was made. If you ask for many messages, it can save them to a file on your own computer and tell you the file name. It never stores your data on a server.

Before you start

What you need

A Kafka cluster you can connect to, with its broker addresses
A configuration file (kafka-mcp.yaml) describing your clusters and endpoints
Kafka credentials if your cluster needs them, like a username and password or TLS certificates
The kafka-mcp binary or container image from the releases page

Good to know

Some tools can change your Kafka data, like creating topics, producing messages, or committing offsets, so use a read-only endpoint unless you really need to write.

Install it with your AI

Add Kafka MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Kafka MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.