mcpField
M
mcp-kafka

mcp-kafka

Local
github.com/brandon-powersCloud & Infra3Updated 84w ago
Repository

About mcp-kafka

mcp-kafka is an MCP server for LLMs working with Apache Kafka and related services. It exposes Kafka operations and inspection tools for Kafka Connect, Burrow, and Cruise Control; the project is still a work in progress.

Key features

  1. 01Consume and produce Kafka messages
  2. 02Inspect clusters, topics, and consumer groups
  3. 03Access Kafka Connect APIs
  4. 04Check Burrow consumer group status
  5. 05Query Cruise Control cluster data

Use cases

  1. 01Consume or publish Kafka messages
  2. 02Inspect topic and consumer group details
  3. 03Review Kafka Connect connectors
  4. 04Check cluster load and partition state

MCP support

The server exposes tools for Kafka, Kafka Connect, Burrow, and Cruise Control, along with topic, connector, and consumer group resources. Available API tools depend on the corresponding environment variables.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Overview

mcp-kafka is a server-side implementation of the model context protocol (MCP) for Apache Kafka. It allows language models (LLM/SLM) to reliably interact with Kafka & its ecosystem, including Kafka Connect, Burrow, & Cruise Control.

NOTE: This is a WIP, changes/potential errors are expected.

Features

The server supports capabilities based on the core Kafka APIs, excluding Streams (for now), along with the Burrow & Cruise Control REST APIs.

TODO

  • Use asyncio and aiohttp.
  • Set env config values in the data class.
  • Finish admin/consumer/producer API support.
  • Support Burrow API.
  • Support CC API.
  • Service + integration tests.
  • Publish to PyPI (uv pip install mcp-kafka)
  • Test Dockerfile & push to Dockerhub (docker pull bkpowers/mcp-kafka)
  • Usage/config/deployment options + demo in README.
  • Consider Strimzi/kcctl integrations.
  • Prompts with auto-complete support for certain resources/tools.
MCP Capabilities
Tools
Kafka
  • consume
  • produce
  • describe_kafka_cluster
  • describe_kafka_topics
  • describe_kafka_consumer_groups
  • describe_kafka_delegation_tokens
  • describe_kafka_log_dirs
  • describe_kafka_configs
  • describe_kafka_acls
Kafka Connect
  • get_kafka_connect_cluster_info
  • get_kafka_connect_config
  • get_kafka_connect_connectors
  • get_kafka_connect_connector_plugins
  • get_kafka_connect_loggers
Burrow
  • burrow_healthcheck
  • burrow_list_clusters
  • burrow_describe_cluster
  • burrow_list_consumers_with_group_detail
  • burrow_list_topics
  • burrow_check_consumer_group_status
Cruise Control
  • cruise_control_get_state
  • cruise_control_get_kafka_cluster_load
  • cruise_control_get_partition_resource_utilization_and_load
  • cruise_control_get_partition_and_replica_state
  • cruise_control_get_optimization_proposals
  • cruise_control_get_user_request_result
Resources
  • topic, connector, consumer group
Prompts

Usage / Configuration

  1. Claude Desktop
  2. Cursor
  3. Windsurf
  4. Langchain MCP adapter
  5. Azure OpenAI
Environment Variables

Supported APIs are (currently) enabled by the presence of their specific environment variable. If none are present, the server responds as empty. If 1 or more variables are present, then the respective tools are also present.

  • KAFKA_BOOTSTRAP_SERVERS: Kafka Admin, Consumer, Producer APIs
  • KAFKA_CONNECT_API_URL: Kafka Connect API
  • KAFKA_BURROW_API_URL: Burrow API
  • KAFKA_CRUISE_CONTROL_API_URL: Cruise Control API

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.