Provides real-time observability into Apache Kafka clusters, enabling AI agents to monitor broker health, track consumer lag, and diagnose issues through natural language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-kafka-observer What's the consumer lag for payment-processor group?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that gives AI agents real-time observability into Apache Kafka clusters. Monitor broker health, track consumer lag, and diagnose issues — all through natural language.
Kafka monitoring typically requires juggling multiple dashboards. This MCP server lets any AI assistant (Claude, ChatGPT, Cursor, VS Code Copilot) query your Kafka cluster directly:
"Is my Kafka cluster healthy?"
"What's the consumer lag for payment-processor group?"
"Why is lag spiking on the orders topic?"
Related MCP server: kafka-mcp
Tool | Description |
| Cluster state: brokers, controller, under-replicated partitions |
| All topics with partition counts and replication factors |
| Detailed config and partition assignments for a topic |
| Per-partition lag for a consumer group |
| Automated root-cause analysis for lag issues |
| Cache hit/miss statistics for observability |
Resource URI | Description |
| High-level cluster summary |
Prompt | Description |
| Step-by-step workflow for diagnosing consumer lag |
| Template for cluster capacity planning |
Python 3.12+
Docker (for local Kafka)
uv package manager
git clone https://github.com/Rushi264/mcp-kafka-observer.git
cd mcp-kafka-observer
# Install dependencies
uv sync
# Start local Kafka
docker compose up -d
# Run tests
uv run pytest -vAdd to your claude_desktop_config.json:
{
"mcpServers": {
"kafka-observer": {
"command": "uv",
"args": [
"--directory", "/path/to/mcp-kafka-observer",
"run", "python", "-m", "mcp_kafka_observer.server"
],
"env": {
"KAFKA_BOOTSTRAP_SERVERS": "localhost:9092"
}
}
}
}MCP Client (Claude / Cursor / VS Code Copilot)
│
│ MCP Protocol (stdio)
▼
mcp-kafka-observer
├── Tools (get_broker_health, get_consumer_lag, ...)
├── Resources (kafka://cluster/overview)
├── Prompts (investigate_lag, capacity_review)
├── TTL Cache (prevents thundering herd on admin API)
└── Analyzer (automated lag diagnosis)
│
│ confluent-kafka AdminClient
▼
Kafka ClusterPython 3.12 with async/await
MCP SDK (FastMCP) — official Anthropic SDK
confluent-kafka — production-grade Kafka client (librdkafka)
Pydantic — structured output validation
Docker Compose — local Kafka for development
# Unit tests (no Kafka needed)
uv run pytest tests/test_server.py -v
# Integration tests (needs Docker Kafka running)
docker compose up -d
uv run pytest tests/test_kafka_client.py -v
# All tests
uv run pytest -v
# Linter
uv run ruff check src/ tests/Set via environment variables or .env file:
Variable | Default | Description |
|
| Kafka broker addresses |
| — | SASL auth mechanism (PLAIN, SCRAM-SHA-256) |
| — | SASL username |
| — | SASL password |
| — | Security protocol (SASL_SSL, SASL_PLAINTEXT) |
MIT
This server cannot be deployed
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.