StreamNative

Provides a standardized interface for AI agents to interact with StreamNative Cloud, Apache Kafka, and Apache Pulsar resources via MCP

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "streamnative-streamnative-mcp-server": {
      "command": "bin/snmcp",
      "args": [
        "stdio",
        "--organization",
        "my-org",
        "--key-file",
        "/path/to/key-file.json"
      ],
      "env": {
        "SNMCP_KEY_FILE": "/path/to/key-file.json",
        "SNMCP_ORGANIZATION": "my-org"
      }
    }
  }
}

You are using the StreamNative MCP Server to connect LLMs and AI agents to StreamNative Cloud resources, Apache Kafka, and Apache Pulsar through a standard MCP interface. This server lets you perform admin, client, and management tasks across these ecosystems from your AI tools, enabling automation and orchestration across messaging platforms.

How to use

You connect your MCP client to the StreamNative MCP Server using one of the available server modes. The stdio mode runs the MCP server as a local process that you execute from your environment. The server can operate with StreamNative Cloud authentication, external Kafka, or external Pulsar connections. When you enable pre-configured Pulsar instances or clusters, certain context-management tools are automatically adjusted.

What you can do with the MCP Server

Interact with StreamNative Cloud resources: manage contexts, switch clusters, and check resource statuses.
Work with Apache Kafka: perform admin tasks (topics, partitions, consumer groups), access Schema Registry, manage Kafka Connect (where available), and produce/consume messages.
Work with Apache Pulsar: manage topics, namespaces, tenants, schemas, and other resources; operate Pulsar clients; manage Functions, Sources, and Sinks.

Recommended usage pattern

Choose a connection mode that fits your environment. If you are testing locally or coordinating with a local LLM workspace, use the stdio server with the simplest authentication path. For production or cloud-based workflows, you can configure external Kafka or Pulsar connections and/or leverage pre-configured StreamNative Cloud contexts.

Notes on tooling and features

You can selectively enable groups of tools with the --features flag to reduce the context size that the AI needs to carry. This helps the model pick appropriate actions and keeps responses focused on the enabled capabilities.

Inspecting and testing the MCP server

Use the MCP inspector tooling to test and verify your MCP server setup. It helps you view available tools, test invocations, and monitor responses.

Available tools

streamnative-cloud

Manage StreamNative Cloud context and check resource logs

functions-as-tools

Dynamically expose deployed Pulsar Functions as MCP tools with automatic input/output schema handling

kafka-admin

Kafka administrative operations including topics, partitions, and consumer groups

kafka-client

Kafka producer/consumer client operations

pulsar-admin

Pulsar administrative operations (tenants, namespaces, topics, schemas, etc.)

pulsar-client

Pulsar producer/consumer client operations

pulsar-functions

Manage Pulsar Functions, Sources, and Sinks

Built by

VeilStrat

AI signals for GTM teams