The Remote StreamNative MCP Server is the managed deployment option for the StreamNative MCP Server. It provides a globally available, organization-aware Model Context Protocol (MCP) service atDocumentation Index
Fetch the complete documentation index at: https://docs.streamnative.io/llms.txt
Use this file to discover all available pages before exploring further.
https://mcp.streamnative.cloud so you can consume managed tools without running infrastructure. You can connect through a root endpoint, an organization endpoint, or a fixed cluster endpoint. It is built on the open-source StreamNative MCP Server.
The remote server uses MCP over HTTP. Configure clients with the full MCP path, such as https://mcp.streamnative.cloud/mcp/x/<organization>/<instance>/<cluster>, not only the host name. Root and organization endpoints start with StreamNative Cloud organization tools. Fixed cluster endpoints start with tools for one Pulsar or Kafka cluster.
Instant access from your IDE
- Launch tooling with a single click in supported editors such as VS Code - no local binaries or runtimes required.
- Construct an organization or cluster endpoint and paste it into any MCP-compatible client to reuse the same catalog across teams and environments.
- Share connections through workspace templates so new collaborators adopt a consistent tool set.
Why use the remote server
- Skip local installation and upgrades - the managed endpoint stays current with the latest StreamNative MCP capabilities.
- Connect from IDEs such as VS Code with a single click or point any MCP-compatible runtime to your cluster endpoint.
- Authenticate with the same StreamNative Cloud credentials you already use for agent deployments.
StreamNative Cloud integration
The managed server authenticates against StreamNative Cloud and understands your organization context. After you sign in, you can:- Browse MCP-enabled clusters that belong to your organization.
- Select a Pulsar or Kafka cluster during an organization-level session and add static cluster tools to the current session.
- Inspect and manage organization-level StreamNative Cloud resources such as service accounts, role bindings, instances, Pulsar clusters, Kafka clusters, and workspaces.
- Read schemas for supported StreamNative Cloud resources before composing JSON manifests.
- Validate organization-level changes with dry-run apply operations before making changes.
- Inspect the status of cluster resources through natural language prompts.
- Interact with StreamNative services using your existing service accounts and permission model.
Platform support
The Remote MCP Server supports all StreamNative Cloud cluster types, including Serverless, Dedicated, BYOC, and BYOC Pro. For details on each type, see Cluster types. The Remote StreamNative MCP Server exposes tools for both Apache Kafka and Apache Pulsar workloads.- Apache Kafka - manage topics, partitions, consumer groups, schema registry artifacts, and run client operations such as producing and consuming messages. The
kafka-admin-kafka-connectfeature ID is accepted, but Kafka Connect tools are not exposed on Remote MCP Kafka cluster sessions in the current preview. - Apache Pulsar - administer tenants, namespaces, topics, and schemas; run client operations; and manage Functions, Sources, and Sinks in read-only mode.
- Orca integrations - surface Pulsar Functions and Orca agents as MCP tools so downstream agents can invoke them directly.
Always current and managed
- StreamNative operates the service so you automatically receive server updates, new tools, and security patches.
- The remote environment mirrors the latest StreamNative Cloud features, keeping documentation and runtime behavior aligned.
- Preview status means feedback can shape the roadmap - share requests through support channels to influence future releases.
Security and authorization
- OAuth 2.1 authorization flows align with the evolving MCP authorization specification, allowing interactive sign-in from IDEs and browsers.
- StreamNative Cloud API Key v2 offers organization-scoped, non-interactive access for automated clients. Send it as
Authorization: Bearer <api-key>. - The server is multi-tenant aware and scopes tool discovery to the resources your identity can access through StreamNative Cloud RBAC.
Endpoint modes
| Mode | Endpoint | Behavior |
|---|---|---|
| Root | https://mcp.streamnative.cloud/mcp | Resolves the organization from the AuthV2 organization audience in your token. Use X-Organization for root OAuth discovery, or omit it during interactive OAuth and select an organization during sign-in. Bearer-token requests must resolve to exactly one organization. |
| Organization | https://mcp.streamnative.cloud/mcp/x/<organization> | Starts with organization-level StreamNative Cloud tools. Use this mode to discover MCP-enabled clusters, switch cluster context, and manage organization resources. |
| Fixed cluster | https://mcp.streamnative.cloud/mcp/x/<organization>/<instance>/<cluster> | Starts directly in one Pulsar or Kafka cluster. Use this mode when you want a stable tool catalog scoped to one cluster and dynamic Pulsar Function or Orca agent tools. |
Getting started
- In the StreamNative Cloud Console, enable MCP for your organization and each cluster that you want to expose. See Governance & Permissions.
- Choose an endpoint mode. For example, organization
o-sndev, instanceinstance-1, and clusterc-clusterresolves tohttps://mcp.streamnative.cloud/mcp/x/o-sndev/instance-1/c-cluster. - Paste the endpoint URL into your MCP client configuration and complete OAuth 2.1 sign-in, or supply a service account API Key v2 in the
Authorizationheader. - Optionally set
X-Organization,X-MCP-Features, andX-MCP-Readonlyheaders to bind root sessions, narrow the tool catalog, or request read-only behavior. See Remote MCP Headers and Feature Selection. - Use
sncloud_context_available_clustersandsncloud_context_use_clusterwhen you start from a root or organization endpoint and need cluster tools in the same session.