convez.ai
MCP ServerDevOps & InfraestruturaAvançado
wklee610

Kafka MCP Server

wklee610/kafka-mcp

Interface LLM para operações completas em clusters Kafka

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que permite LLMs interagirem com clusters Apache Kafka. Oferece gerenciamento completo de clusters, tópicos, grupos de consumidores, configurações e mensagens através de ferramentas estruturadas.

Instalação

$npx convez-ai wklee610/kafka-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
14
Forks
3
Acompanhando
1
Saúde
42%
Último commit
há 2 meses
Versão
2.0.0
Issues abertas
0
Contribuidores
1

Casos de uso

  • Monitoramento e diagnóstico de clusters Kafka via conversação
  • Automação de operações de tópicos e consumer groups
  • Produção e consumo de mensagens através de IA
  • Auditoria e rewind de offsets com validação de estado
  • Gestão dinâmica de configurações de brokers e tópicos

Veredito

Implementação sólida e bem documentada de MCP para Kafka com Python 3.10+. Cobre casos de uso reais (cluster ops, consumer groups, offset management) com suporte a auditoria. Recomendado para equipes que operam Kafka em produção e buscam automação via LLM, exigindo conhecimento prévio de Kafka e MCP.

README

A tradução para o português deste README ainda está na fila.

Kafka MCP Server

Python License Kafka MCP


An MCP server implementation for Kafka, allowing LLMs to interact with and manage Kafka clusters.

Features

  • Cluster Management: View broker details describe_cluster, describe_brokers.
  • Topic Management: List list_topics, create create_topic, delete delete_topic, describe describe_topic, and increase partitions create_partitions.
  • Configuration Management: View describe_configs and modify alter_configs dynamic configs for topics, brokers, and groups.
  • Consumer Groups: List list_consumer_groups, describe describe_consumer_group, and securely manage offsets with reset_consumer_group_offset and rewind_consumer_group_offset_by_timestamp. Advanced tools include state validation, dry runs, and execution audit logging.
  • Messaging: Consume messages consume_messages (from beginning, latest, or specific offsets) and produce messages produce_message.

Prerequisites

  • Python 3.10+
  • uv package manager (recommended)
  • A running Kafka cluster (e.g., local Docker, Confluent Cloud, etc.)

Installation

  1. Clone the repository.
  2. Install dependencies:
    uv sync
    

Configuration

The server requires the KAFKA_BOOTSTRAP_SERVERS environment variable.

  • KAFKA_BOOTSTRAP_SERVERS: Comma-separated list of broker urls (e.g., localhost:9092).
  • KAFKA_CLIENT_ID: (Optional) Client ID for connection (default: kafka-mcp).

Usage

Running the Server

You can run the server directly using uv or python, or use Docker.

Using uv (Recommended)

export KAFKA_BOOTSTRAP_SERVERS=localhost:9092
uv run kafka-mcp

Using Docker

  1. Build the Docker image:

    docker build -t kafka-mcp .
    
  2. Run the container:

    docker run -i --rm -e KAFKA_BOOTSTRAP_SERVERS=host.docker.internal:9092 kafka-mcp
    

    (Note: Use host.docker.internal instead of localhost if your Kafka cluster is running on the host machine.)

Claude Desktop Configuration

Add the following to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "kafka": {
      "command": "<uv PATH>",
      "args": [
        "--directory",
        "<kafka-mcp PATH>",
        "run",
        "kafka-mcp"
      ],
      "env": {
        "KAFKA_BOOTSTRAP_SERVERS": "localhost:9092"
      }
    }
  }
}

Debugging / Development

To verify that the server can start and connect to your Kafka cluster (ensure your Kafka is running first):

# Set your bootstrap server
export KAFKA_BOOTSTRAP_SERVERS=localhost:9092

# Run a quick check
uv run python -c "from src.kafka_mcp import main; print('Imports successful')"

Available Tools

CategoryTool NameDescription
Clusterdescribe_clusterGet cluster metadata (controller, brokers).
describe_brokersList all brokers.
Topicslist_topicsList all available topics.
describe_topicGet detailed info (partitions, replicas) for a topic.
create_topicCreate a new topic with partitions/replication factor.
delete_topicDelete a topic.
create_partitionsIncrease partitions for a topic.
Configsdescribe_configsView dynamic configs for topic/broker/group.
alter_configsUpdate dynamic configs.
Consumerslist_consumer_groupsList all active consumer groups.
describe_consumer_groupGet members and state of a group.
get_consumer_group_offsetsGet committed offset, high/low watermarks, and calculate total lag for a topic.
reset_consumer_group_offsetSafely change consumer group offsets to earliest, latest, or a specific offset.
rewind_consumer_group_offset_by_timestampRewind/advance consumer group offsets securely based on a timestamp.
Messagesconsume_messagesConsume messages from a topic (supports offsets, limits).
produce_messageSend a message to a topic.

Project Structure

src/kafka_mcp/
├── configs/       # Configuration handling
├── connections/   # Kafka client factories (singleton)
├── tools/         # Tool implementations
│   ├── admin.py     # Topic & Config management
│   ├── cluster.py   # Cluster metadata
│   ├── consumer.py  # Consumer group & message consumption
│   └── producer.py  # Message production
└── main.py        # Entry point & MCP tool registration

Troubleshooting

  • Connection Refused: Ensure KAFKA_BOOTSTRAP_SERVERS is correct and reachable.

TODO

  • SASL
  • JMX
Ver o original no GitHub

Bom para

Relacionados