Kafka MCP Server

@MCP-Mirror

リポジトリ

基本情報

カテゴリ

その他

ライセンス

Apache-2.0 license

トランスポート

stdio

作者

MCP-Mirror

Kafka MCP Server について

Mirror of

#kafka #mcp-server#message-protocol

Kafka MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pavanjava_kafka_mcp_server": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Kafka MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Kafka MCP Server?

A Message Context Protocol (MCP) server that integrates with Apache Kafka, providing publish and consume functionalities for LLM and agentic applications. It allows AI models to interact with Kafka topics through a standardized interface.

How to use Kafka MCP Server?

Install dependencies (pip install -r requirements.txt), configure a .env file with Kafka connection settings, then run python main.py --transport stdio. Supports stdio (default) and sse transports. Can be integrated with Claude Desktop via its MCP configuration.

Key features of Kafka MCP Server

Publish messages to a configured Kafka topic
Consume messages from a configured Kafka topic
Supports configurable Kafka bootstrap servers, topic name, and consumer group
Customizable tool descriptions via environment variables
Runs over stdio or SSE transports

Use cases of Kafka MCP Server

Enable an LLM to publish structured data to a Kafka topic
Allow an AI agent to consume and process messages from a Kafka stream
Integrate Kafka messaging into a Claude Desktop workflow

よくある質問

What are the prerequisites?

Python 3.8+, a running Apache Kafka instance, and installation of dependencies `aiokafka`, `python-dotenv`, `pydantic-settings`, and `mcp-server`.

How do I configure the server?

Create a `.env` file in the project root with `KAFKA_BOOTSTRAP_SERVERS`, `TOPIC_NAME`, `IS_TOPIC_READ_FROM_BEGINNING`, and `DEFAULT_GROUP_ID_FOR_CONSUMER`. Optional `TOOL_PUBLISH_DESCRIPTION` and `TOOL_CONSUME_DESCRIPTION` can override tool descriptions.

What transport options are available?

The server supports `stdio` (standard input/output) and `sse` (Server-Sent Events). Use the `--transport` flag when running `main.py`.

Can I customize the tool names or descriptions?

Yes, by setting `TOOL_PUBLISH_DESCRIPTION` and `TOOL_CONSUME_DESCRIPTION` in the `.env` file you can provide custom descriptions for the publish and consume tools.

Are consumed messages re-readable?

No. Once a message is read from the topic it cannot be read again using the same consumer group. The server uses a configurable consumer group (`DEFAULT_GROUP_ID_FOR_CONSUMER`).

「その他」の他のコンテンツ

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

ICSS

chokcoco

不止于 CSS

20.7K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。