What is the purpose of this server?
It enables LLMs to publish and consume events from Kafka topics through the MCP protocol, bridging AI agents with Kafka-based event streams.
@boufnichel
Basic information
An MCP server for processing Kafka events and enabling LLMs to interact with event streams
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Mcp Kafka Processor is an MCP server that provides event processing capabilities through Kafka integration. It allows Large Language Models to interact with Kafka topics through the Model Context Protocol, enabling publish and consume operations for event-driven AI workflows.
Clone the repository, install dependencies with npm install, and build with npm run build. Configure the Kafka broker using the KAFKA_BROKERS environment variable (default localhost:9092), then add the server to your Claude Desktop configuration by specifying the build/index.js path and environment variable in claude_desktop_config.json.
It enables LLMs to publish and consume events from Kafka topics through the MCP protocol, bridging AI agents with Kafka-based event streams.
Node.js 16 or higher, an accessible Kafka broker, and TypeScript knowledge for development.
Set the `KAFKA_BROKERS` environment variable to a comma-separated list of broker addresses (default is `localhost:9092`).
Two tools: `publish-event` (send a message to a topic) and `consume-events` (receive messages from a topic). Both require a `topic` parameter; consume-events also accepts an optional `maxMessages` parameter.
Yes, the `consume-events` tool has a `maxMessages` parameter that defaults to 10.
Find the AI tells in your prose. Deterministic, local, runs in CI. MCP server + CLI + Action.

Spark Inventory’s MCP server lets Claude, ChatGPT and other AI agents work with your inventory. They can check stock, read Demand ESP forecasts (a model per SKU picked by backtest, with stockout correction and seasonalit

Snipzr (snipzr.com) is a URL shortener. Its remote MCP server lets your AI assistant create and batch-create short links on your own domain, update and list them, read cookie-less click stats with bots shown separately,

Run your business from your AI assistant: websites, online shops, forms, invoices, domains, WordPress, media, brand, print and social media — one KENJTEC account, OAuth sign-in, twelve languages.
PayPerFax MCP server: send a fax from your AI assistant. Pay per fax, no account.
Comments