StreamNative MCP Server Overview

The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.

Developed by Anthropic, the Model Context Protocol (MCP) enables AI agents like Claude to seamlessly integrate with Tavily’s advanced search and data extraction capabilities. This integration provides AI models with real-time access to web information, complete with sophisticated filtering options and domain-specific search features.

StreamNative MCP Server is an Open Source project that enables AI agents to integrating StreamNative Cloud resources and Apache Kafka/Pulsar messaging systems.

Any MCP Client configured to use the StreamNative MCP Server can use its AI capabilities to help you:

• Manage StreamNative Cloud resources:
  • 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
  • Exposes Pulsar Functions as MCP Tools
• 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.

Prerequisites

Before you begin, make sure you have the following:

Operating systems

The StreamNative MCP Server is compatible with the following operating systems and architectures only:

• macOS with 64-bit Intel chips (Darwin AMD64)
• macOS with Apple chips (Darwin ARM64)
• Windows with 64-bit Intel or AMD chips (Microsoft Windows AMD64)
• Linux with 64-bit Intel or AMD chips (Linux AMD64)
• Linux with 64-bit ARM chips (Linux ARM64)

Network access

When the StreamNative MCP Server interacts with StreamNative Cloud, it requires network access to the following domains:

• api.streamnative.cloud
• auth.streamnative.cloud
• log.streamnative.cloud

StreamNative Cloud resources

• Access to StreamNative Cloud.
• A StreamNative Cloud organization
• A StreamNative Cloud service account created in the organization, details can be found in Manage Service Accounts. Download the service account key file as a JSON file.

Installation

Please follow the installation guide to install the StreamNative MCP Server.

Setup your MCP Client

The StreamNative MCP Server can work with any MCP client that supports standard I/O (stdio) or SSE transport.

Please follow the Start the MCP Server and Integration with MCP Clients to setup your MCP Client.

Fine grained access control to the StreamNative MCP Server

The StreamNative MCP Server supports fine grained access control. You can configure the StreamNative MCP Server to allow or deny access to specific resources and operations.

You may control the access by following Control Access to StreamNative Cloud to make sure your StreamNative Cloud Service Account used to run the StreamNative MCP Server has the limited permissions.

MCP server capabilities

The StreamNative MCP Server supports enabling or disabling specific groups of functionalities via the --features flag. This allows you to control which MCP tools are available to your AI tools. Enabling only the toolsets that you need can help the LLM with tool choice and reduce the context size.

Please follow the Tool Configuration to configure the StreamNative MCP Server with the desired toolset.

Provide feedback

If you have any feedback or suggestions, please open an issue on the GitHub repository.