一个面向开发者的MCP服务器，桥接Kafka和Pulsar协议——由StreamNative打造❤️，面向一个以流媒体为先的代理型未来。
概览
一款用于将AI代理与StreamNative云资源及Apache Kafka/Pulsar消息系统集成的模型上下文协议（MCP）服务器。 StreamNative MCP 服务器为大型语言模型（LLM）和 AI 代理提供了与 StreamNative 云服务、Apache Kafka 和 Apache Pulsar 交互的标准接口。该实现遵循模型上下文协议规范，使 AI 应用能够通过标准化接口访问消息服务。 服务器目前协商MCP协议版本2025-11-25、2025-06-18、2025-03-26和2024-11-05。默认偏好为2025-11-25，而较旧客户端仍通过协议协商支持。
概述（AI 翻译）
一款用于将AI代理与StreamNative云资源及Apache Kafka/Pulsar消息系统集成的模型上下文协议（MCP）服务器。
概述
StreamNative MCP 服务器为大型语言模型（LLM）和 AI 代理提供了与 StreamNative 云服务、Apache Kafka 和 Apache Pulsar 交互的标准接口。该实现遵循模型上下文协议规范，使 AI 应用能够通过标准化接口访问消息服务。
服务器目前协商MCP协议版本 2025-11-25、2025-06-18、2025-03-26 和 2024-11-05。默认优先级为 2025-11-25，而较旧的客户端仍通过协议协商支持。
特色
- StreamNative 云集成：
- 通过认证连接StreamNative Cloud资源
- 切换到组织内可用的集群
- 描述集群资源的状态
- Apache Kafka 支持：与包括以下在内的 Apache Kafka 资源交互：
- Kafka 管理操作（主题、分区、消费者组）
- 模式注册表操作
- Kafka Connect 操作（*）
- Kafka 客户运营（生产者、消费者）
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
StreamNative MCP Server
A Model Context Protocol (MCP) server for integrating AI agents with StreamNative Cloud resources and Apache Kafka/Pulsar messaging systems.
Overview
StreamNative MCP Server provides a standard interface for LLMs (Large Language Models) and AI agents to interact with StreamNative Cloud services, Apache Kafka, and Apache Pulsar. This implementation follows the Model Context Protocol specification, enabling AI applications to access messaging services through a standardized interface.
The server currently negotiates MCP protocol versions 2025-11-25, 2025-06-18, 2025-03-26, and 2024-11-05. The default preference is 2025-11-25, while older clients remain supported through protocol negotiation.
Features
- StreamNative Cloud Integration:
- Connect to StreamNative Cloud resources with authentication
- Switch to clusters available in your organization
- Describe the status of clusters resources
- Apache Kafka Support: Interact with Apache Kafka resources including:
- Kafka Admin operations (topics, partitions, consumer groups)
- Schema Registry operations
- Kafka Connect operations (*)
- Kafka Client operations (producers, consumers)
- Apache Pulsar Support: Interact with Apache Pulsar resources including:
- Pulsar Admin operations (topics, namespaces, tenants, schemas, etc.)
- Pulsar Client operations (producers, consumers)
- Functions, Sources, and Sinks management
- Read-only MCP resources for context, catalog, and bounded admin summaries
- Multiple Connection Options:
- Connect to StreamNative Cloud with service account authentication
- Connect directly to external Apache Kafka clusters
- Connect directly to external Apache Pulsar clusters
*: The Kafka Connect operations are only tested and verified on StreamNative Cloud.
Installation
Homebrew (macOS and Linux)
The easiest way to install streamnative-mcp-server is using Homebrew:
# Add the tap repository
brew tap streamnative/streamnative
# Install streamnative-mcp-server
brew install streamnative/streamnative/snmcp
Docker Image
StreamNative MCP Server releases the Docker Image to streamnative/snmcp, and it can be used to run both stdio server and sse server via docker command.
# Pull image from Docker Hub
docker pull streamnative/snmcp
Helm Chart (Kubernetes)
See charts/snmcp/README.md for Helm installation via the StreamNative chart repository.
From Github Release
Visit https://github.com/streamnative/streamnative-mcp-server/releases to get the latest binary of StreamNative MCP Server.
From Source
# Clone the repository
git clone https://github.com/streamnative/streamnative-mcp-server.git
cd streamnative-mcp-server
go mod tidy
go mod download
# Build the binary
make
Usage
Prerequisites
安装
docker run -i --rm -e SNMCP_ORGANIZATION -e SNMCP_KEY_FILE -v ${STREAMNATIVE_CLOUD_KEY_FILE}:/key.json streamnative/snmcp stdio配置
{
"mcpServers": {
"mcp-streamnative": {
"command": "${PATH_TO_SNMCP}/bin/snmcp",
"args": [
"stdio",
"--organization",
"${STREAMNATIVE_CLOUD_ORGANIZATION_ID}",
"--key-file",
"${STREAMNATIVE_CLOUD_KEY_FILE}"
]
}
}
}