StreamNative
Developer-friendly MCP server bridging Kafka and Pulsar protocols—built with ❤️ by StreamNative for an agentic, streaming-first future.
What is StreamNative?
StreamNative is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to developer-friendly mcp server bridging kafka and pulsar protocols—built with ❤️ by streamnative for an agentic, streaming-first future.
Developer-friendly MCP server bridging Kafka and Pulsar protocols—built with ❤️ by StreamNative for an agentic, streaming-first future.
This server falls under the Data Science & ML and APIs categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Developer-friendly MCP server bridging Kafka and Pulsar prot
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx streamnativeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use StreamNative
StreamNative MCP Server (snmcp) is a Go-based MCP integration that bridges Apache Kafka and Apache Pulsar streaming platforms with AI agents, enabling natural-language interaction with message brokers, topics, consumer groups, schemas, and streaming infrastructure. It supports StreamNative Cloud deployments as well as external self-managed Pulsar and Kafka clusters, with modular feature sets selectable at startup. Platform engineers and data engineers can use it to produce and consume messages, inspect topic configurations, manage Pulsar Functions, monitor schemas, and administer clusters — all through conversational AI without needing to memorize CLI syntax.
Prerequisites
- Access to a StreamNative Cloud organization, a self-managed Apache Pulsar cluster, or an Apache Kafka cluster
- For StreamNative Cloud: a service account key JSON file and organization ID
- For external Pulsar: broker web service URL and an auth token (or auth plugin credentials)
- For external Kafka: bootstrap server address and SASL/TLS credentials if required
- An MCP-compatible client such as Claude Desktop; Homebrew for the easiest binary install on macOS/Linux
Install snmcp
Install the snmcp binary via Homebrew on macOS or Linux. Alternatively, pull the Docker image or build from source.
# Homebrew
brew tap streamnative/streamnative
brew install streamnative/streamnative/snmcp
# Docker
docker pull streamnative/snmcpConfigure credentials for your platform
Set environment variables or CLI flags for your streaming platform. For StreamNative Cloud, provide your organization ID and service account key file.
# StreamNative Cloud
export SNMCP_ORGANIZATION=your-org-id
export SNMCP_KEY_FILE=/path/to/service-account-key.json
# External Kafka
# Pass --kafka-bootstrap-servers and auth flags at runtimeStart the server in stdio mode (StreamNative Cloud)
Run snmcp in stdio mode for direct MCP client integration with StreamNative Cloud.
bin/snmcp stdio --organization my-org --key-file /path/to/key.jsonOr start with external Pulsar via SSE
Use SSE transport for external Pulsar clusters, optionally enabling multi-user session mode.
bin/snmcp sse --http-addr :9090 --use-external-pulsar \
--pulsar-web-service-url http://pulsar.example.com:8080 \
--pulsar-token your-auth-tokenSelect feature sets
Use the --features flag to enable only the tool categories you need, reducing the MCP tool surface exposed to the agent.
# Enable all Kafka tools
bin/snmcp stdio --features all-kafka --kafka-bootstrap-servers broker:9092
# Enable all Pulsar tools
bin/snmcp stdio --features all-pulsar --use-external-pulsar \
--pulsar-web-service-url http://pulsar.example.com:8080Configure your MCP client
Add snmcp to your Claude Desktop configuration for StreamNative Cloud access.
StreamNative Examples
Client configuration
Add snmcp to Claude Desktop for StreamNative Cloud in stdio mode with credentials from environment variables.
{
"mcpServers": {
"streamnative": {
"command": "snmcp",
"args": ["stdio", "--features", "all-pulsar"],
"env": {
"SNMCP_ORGANIZATION": "your-org-id",
"SNMCP_KEY_FILE": "/path/to/service-account-key.json"
}
}
}
}Prompts to try
Manage Kafka and Pulsar streaming infrastructure through natural-language conversation.
- "List all Kafka topics in the cluster and show their partition counts."
- "Produce a test message 'hello world' to the topic 'orders'."
- "Show me the consumer group lag for group 'payment-processor'."
- "List all Pulsar namespaces in tenant 'my-tenant'."
- "What Pulsar Functions are currently running and what are their statuses?"
- "Show me the schema registered for topic 'user-events'."
- "Switch to my staging StreamNative Cloud cluster."Troubleshooting StreamNative
Authentication fails for StreamNative Cloud
Verify that SNMCP_KEY_FILE points to a valid service account JSON key file and that SNMCP_ORGANIZATION matches your exact organization ID from the StreamNative Cloud console. Service accounts must have appropriate role bindings in the organization.
Kafka tools are not available or tool calls fail with connection refused
Ensure you started snmcp with '--features all-kafka' or 'kafka-client' and that '--kafka-bootstrap-servers' points to a reachable broker. Check that TLS/SASL settings match your Kafka cluster's security configuration.
SSE server starts but MCP client cannot connect
Verify the --http-addr port is not blocked by a firewall and that the MCP client is configured to use the SSE transport URL (e.g., http://localhost:9090/sse). For multi-user mode, Bearer tokens must be included in the Authorization header.
Frequently Asked Questions about StreamNative
What is StreamNative?
StreamNative is a Model Context Protocol (MCP) server that developer-friendly mcp server bridging kafka and pulsar protocols—built with ❤️ by streamnative for an agentic, streaming-first future. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install StreamNative?
Follow the installation instructions on the StreamNative GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with StreamNative?
StreamNative works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is StreamNative free to use?
Yes, StreamNative is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
StreamNative Alternatives — Similar Data Science & ML Servers
Looking for alternatives to StreamNative? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up StreamNative in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use StreamNative?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.