kafka-mcp¶
Apache Kafka API + MCP Server + A2A Agent for the agent-utilities ecosystem — topics, records, consumer groups, brokers, and ACLs over the Confluent REST Proxy, with an optional native (direct-to-broker) client.
Official documentation
This site is the canonical reference for kafka-mcp, maintained alongside every
release.
Overview¶
kafka-mcp wraps the Apache Kafka administration and data-plane surface with typed,
deterministic MCP tools, and ships an optional Pydantic-AI agent server. It provides:
KafkaApi— arequests-based REST facade over the Confluent REST Proxy v3 (with v2 consumer helpers), organized by Kafka resource: clusters, topics, partitions, records, consumer groups, brokers, and ACLs.- Six MCP tools — action-dispatch wrappers (
kafka_topics,kafka_partitions,kafka_records,kafka_groups,kafka_cluster,kafka_native) that expose the full surface to an agent or policy router. - An optional native client (
kafka-mcp[native]) that produces, consumes, and administers topics directly against brokers viaconfluent-kafka.
The active cluster id is resolved lazily — set KAFKA_CLUSTER_ID to pin it, or let
the client cache the first cluster the REST Proxy returns.
Explore the documentation¶
- Installation — pip, source, extras, and the prebuilt Docker image.
- Deployment — run the MCP and agent servers, Docker Compose, Caddy + Technitium.
- Usage — the MCP tools, the
KafkaApiclient, and the CLI. - Backing Platform — deploy Apache Kafka with Docker.
- Architecture — the layered REST client and tool surface.
- Concepts — the
CONCEPT:KAFKA-*registry.
Quick start¶
Connect it to a Confluent REST Proxy in front of your Kafka cluster:
export KAFKA_REST_URL=http://your-rest-proxy:8082
kafka-mcp --transport streamable-http --host 0.0.0.0 --port 8000
See Installation and Deployment for the full matrix (PyPI extras, Docker image, all transports, the agent server, reverse proxy, DNS).