tuannvm/kafka-mcp-server

A Model Context Protocol (MCP) server for Apache Kafka implemented in Go, leveraging franz-go and mcp-go.
This server provides an implementation for interacting with Kafka via the MCP protocol, enabling LLM models to perform common Kafka operations through a standardized interface.
Overview
The Kafka MCP Server bridges the gap between LLM models and Apache Kafka, allowing them to:
- Produce and consume messages from topics
- List, describe, and manage topics
- Monitor and manage consumer groups
- Assess cluster health and configuration
- Execute standard Kafka operations
All through the standardized Model Context Protocol (MCP).
Architecture
**How it works:**
1. **MCP Clients** (AI applications) connect to the Kafka MCP Server via stdio or HTTP transport
2. **MCP Server** exposes three types of capabilities:
- **Tools** - Direct Kafka operations (produce/consume messages, describe topics, etc.)
- **Resources** - Cluster health reports and diagnostics
- **Prompts** - Pre-configured workflows for common operations
3. **Kafka Client Wrapper** handles all Kafka communication using the franz-go library
4. **Apache Kafka Cluster** processes the actual message streaming and storage
**Transport Modes:**
- **STDIO**: Default mode, ideal for local MCP clients (Claude Desktop, Cursor, etc.)
- **HTTP**: Enables remote access with optional OAuth 2.1 authentication
Key Features
- **Kafka Integration**: Implementation of common Kafka operations via MCP
- **Security**:
- Support for SASL (PLAIN, SCRAM-SHA-256, SCRAM-SHA-512) and TLS authentication
- OAuth 2.1 authentication for HTTP transport (Native and Proxy modes)
- Support for Okta, Google, Azure AD, and HMAC providers
- **Flexible Transport**: STDIO for local clients, HTTP for remote access
- **Error Handling**: Error handling with meaningful feedback
- **Configuration Options**: Customizable for different environments
- **Pre-Configured Prompts**: Set of prompts for common Kafka operations
- **Compatibility**: Works with MCP-compatible LLM models
Getting Started
Prerequisites
- Go 1.24 or later
- Docker (for running integration tests)
- Access to a Kafka cluster
Installation
Homebrew (macOS and Linux)
The easiest way to install kafka-mcp-server is using Homebrew:
To update to the latest version:
From Source
MCP Client Integration
This MCP server can be integrated with several AI applications. Below are platform-specific instructions:
Cursor
Edit ~/.cursor/mcp.json and add the kafka-mcp-server configuration:
Claude Desktop
Edit your Claude configuration file and add the server:
- **macOS**: ~/Library/Application Support/Claude/claude_desktop_config.json
- **Windows**: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop to apply changes.
Claude Code
To use with Claude Code, add the server using the built-in MCP configuration command:
**Other useful commands:**
ChatWise
1. Open ChatWise → Settings → Tools → "+" → "Command Line MCP"
2. Configure:
- **ID**: kafka
- **Command**: kafka-mcp-server
- **Args**: (leave empty)
- **Env**: Add environment variables:
Simplify Configuration with mcpenetes
Managing MCP server configurations across multiple clients can become challenging. mcpenetes is a dedicated tool that makes this process significantly easier:
Key Features
- **Interactive Search**: Find and select Kafka MCP server configurations with a simple command
- **Apply Everywhere**: Automatically sync configurations across all your MCP clients
- **Configuration Backup**: Safely backup existing configurations before making changes
- **Restore**: Easily revert to previous configurations if needed
Quick Start with mcpenetes
With mcpenetes, you can maintain multiple Kafka configurations (development, production, etc.) and switch between them instantly across all your clients (Cursor, Claude Desktop, Windsurf, ChatWise) without manually editing each client's configuration files.