A Model Context Protocol server for Apache Kafka. It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) monitor and manage Kafka clusters — topics, partitions, configs, and consumer…
mcp-kafka is an MCP project maintained in the dockndevai/mcp-kafka repository. The maintainer describes its purpose as “A Model Context Protocol server for Apache Kafka. It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) monitor and manage Kafka clusters — topics…”. Read the project documentation for the complete scope.
The documented npm package is @dockndevai/mcp-kafka. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares KAFKA_BROKERS, KAFKA_MODE. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"kafka": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-kafka"
],
"env": {
"KAFKA_BROKERS": "localhost:9092",
"KAFKA_MODE": "read-only"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| KAFKA_BROKERS | Declared in the maintainer’s client configuration. | Check documentation |
| KAFKA_MODE | Declared in the maintainer’s client configuration. | Check documentation |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Klaviyo MCP: campaigns, flows, segments, metrics, reports, profiles across many accounts. 24 tools.
Prometheus MCP server for AI agents: PromQL queries, alert explanations, series discovery.
MetricDuck is a hosted remote MCP server. It answers questions about public companies from their SEC filings: 10-K, 10-Q and 8-K text, financial statements and metrics, earnings calls and guidance.…
Read-only scan of a public GitHub repo for leaked secrets, with a 0-100 grade.