MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP Server for Apache Kafka
Apache-2.0 ★ 14 -
mcp-kafkagithub.com/williajm/mcp_kafkaupdated this year
Model Context Protocol server for Apache Kafka
pypi MIT -
MCP server for Apache Kafka — monitor & manage clusters, topics, and consumer groups (with lag), with security modes and access-control flags.
npm MIT ★ 1 -
mcp-kafkagithub.com/gAmUssA/mcp-kafkaupdated this year
mcp server for Apache Kafka, Schema Registry and Apache Flink
MIT ★ 13 -
基于 Python 与 FastMCP 构建的生产级 Apache Kafka 模型上下文协议 (MCP) 服务端,具备双重安全防线、零位移侵入消息采样与 Stdio/SSE 双模网关
pypi Apache-2.0 -
Read-only MCP server for Apache NiFi, ClickHouse and Kafka: OIDC or proxy auth, per-user audit, secret masking, two-lock read-only
pypi Apache-2.0 -
A comprehensive Model Context Protocol (MCP) server for Apache Kafka operations. Enables seamless Kafka cluster management through Claude Desktop and other MCP clients with support for topics, messages, consumer groups, and real-time monitoring
NOASSERTION ★ 2 -
Open-source operations console for Apache Artemis, Apache Kafka and RabbitMQ: every cluster in one estate, consumer lag shown as the estimate it is, previews before anything destructive, and an approval gate for people and AI assistants.
npm Apache-2.0 ★ 10 -
Secure, vendor-neutral MCP gateway for operating Apache Kafka with AI agents
Apache-2.0 -
An MCP server for Apache Kafka & its ecosystem.
Apache-2.0 ★ 3 -
Desktop client for Apache Kafka and RabbitMQ — browse topics & queues, produce/consume, manage consumer groups, schemas and connectors, with built-in terminal tabs and an MCP server for Claude Code. Electron + TypeScript.
Apache-2.0 ★ 2 -
MCP server for Apache Kafka running on Cloudera Data Flow (CDF)
-
kafka-mcp-servergithub.com/tuannvm/kafka-mcp-serverupdated this year
A Model Context Protocol (MCP) server for Apache Kafka implemented in Go, leveraging franz-go and mcp-go.
go ★ 57 -
zaksway-kafka-mcpgithub.com/zakariahere/zaksway-kafka-mcpupdated this year
An MCP server exposing Apache Kafka admin and data-plane operations as tools for AI agents.
pypi -
streamops-agentgithub.com/atomicdragonranch/streamops-agentupdated this year
AI-powered operations agent for Apache Flink streaming pipelines. Monitors Kafka and Flink metrics, detects anomalies, and recommends scaling and configuration actions via an MCP server interface.
MIT ★ 1 -
Real-time bookstore analytics with Apache Kafka Streams, Kafka Connect and PostgreSQL, queried through a REST API and an MCP/LangChain AI agent.
-
kk-mcpgithub.com/wangyajun/kk-mcpupdated this year
Kafka MCP Server - A Model Context Protocol server for Apache Kafka integration
pypi MIT -
Runnable Strimzi lab + production reference for operating Apache Kafka on Kubernetes the lifecycle way — provision, upgrade, DR with MirrorMaker 2, and read-only agent triage via @dockndevai/mcp-kafka.
MIT ★ 3 -
A production-ready Model Context Protocol (MCP) server for Apache Kafka. Features Information Flow Control (IFC) sandboxing, granular namespace isolation, and strict bounded buffers to securely bridge autonomous AI agents with enterprise streaming infrastructure.
pypi Apache-2.0 ★ 2 -
AI-Powered Kafka Management via Model Control Protocol (MCP) KafkaIQ is an intelligent Kafka management tool that exposes Apache Kafka operations through the Model Control Protocol (MCP), enabling AI assistants to seamlessly interact with and manage Kafka clusters through natural language commands.
-
EcomIQ-AI-Powered-Operational-Intelligence-Platform-github.com/Kaustubh-Indulkar/EcomIQ-AI-Powered-Operational-Intelligence-Platform-updated this year
EcomIQ is an AI-powered operational intelligence platform that combines Apache Kafka, Spark Structured Streaming, and PostgreSQL to process real-time e-commerce data. It leverages FastAPI, Google Gemini, and FastMCP to deliver conversational business insights through natural language queries.
-
KafDeskno update data
Apache Kafka for AI agents: topics, records, consumer lag and schemas. Read-only by default.
mcpb -
A comprehensive Message Control Protocol (MCP) server for Kafka Schema Registry.
pypi MIT ★ 32 -
strimzi-kafka-cligithub.com/SystemCraftsman/strimzi-kafka-cliupdated this year
Command Line Interface and MCP Server for the Strimzi Kafka Operator
pypi Apache-2.0 ★ 91 -
Developer-friendly MCP server bridging Kafka and Pulsar protocols—built with ❤️ by StreamNative for an agentic, streaming-first future.
go Apache-2.0 ★ 24 -
Safe-by-default MCP server for Kafka: scoped read tools, redacted DLQ browsing, and replay gated by dry-run plans and single-use approval tokens. Java 21, Spring AI.
MIT -
Config-driven Kafka-to-HTTP callback bridge: consume, retry, dead-letter, and produce, with an MCP interface for AI agents
Apache-2.0 ★ 1 -
Self-hosted messaging console for eight protocols. Inspect messages, investigate Kafka lag, bridge brokers, and connect AI tools through MCP.
★ 1 -
Real-time transaction fraud detection: Kafka + Spark Structured Streaming + NVIDIA NIM explanations + MCP risk-status tool
-
Multi-tenant operational intelligence platform AI control plane in Go/K8s. Features custom operator, Kafka ingestion, Temporal workflows, MCP LLM gateway, pgvector hybrid search, OpenTelemetry distributed tracing, ArgoCD GitOps, and Redis semantic caching
Apache-2.0 ★ 3 -
Real-time streaming data contract gatekeeper & zero-trust Delta Lake quarantine engine. Features PySpark Structured Streaming, Kafka (KRaft), Model Context Protocol (MCP) shift-left validation, dbt/DuckDB analytics marts, and automated LLM incident triage handling 40K+ events/sec with sub-millisecond latency.
MIT -
High-throughput, event-driven voice orchestration and call center platform with zero-PSTN cost testing, reactive Netty audio streaming, and MCP-powered triage.
-
Apache Camel routes in Rust, and the reliable action layer for AI agents: routes as MCP tools with schema checks, approvals, run-once and audit. ~230 components, std-only, one native binary: 3 ms startup, up to 54x less memory, 1.7-8.7x Camel's throughput. A Cameleering project.
cargo Apache-2.0 ★ 3 -
Query it, chart it, share it — then hand it to your agent. SQL, dashboards, notebooks and alerts over 60+ data sources, with an MCP server that keeps your permissions. Self-hosted, Apache 2.0.
Apache-2.0 ★ 2