Documentation Index
Fetch the complete documentation index at: https://docs.streamnative.io/llms.txt
Use this file to discover all available pages before exploring further.
The StreamNative MCP Server organizes tools into tool groups. Each group contains related operations that you can enable or disable together. Pulsar, Kafka, and dynamic feature IDs apply to both the Remote MCP Server and the local MCP Server, unless a note states otherwise. StreamNative Cloud organization feature IDs apply to Remote MCP organization-level sessions.
Organization-level sessions expose StreamNative Cloud tools for cluster discovery and control-plane resources. For workflow details, see Organization-Level Tools.
| Feature ID | Tools | Description |
|---|
streamnative-cloud or cloud | All sncloud_* tools | Enable all StreamNative Cloud organization tool families. |
sncloud_context or sncloud-context | sncloud_context_available_clusters, sncloud_context_use_cluster, sncloud_context_reset | List MCP-enabled clusters, select a cluster, or reset cluster context. The global identity tool sncloud_context_whoami is always available. |
sncloud_byoc or sncloud-byoc | sncloud_resource_catalog, sncloud_resource_schema, sncloud_byoc_read, sncloud_byoc_write | Read or manage BYOC resources such as CloudConnection, CloudEnvironment, Volume, and PoolMember. |
sncloud_identity or sncloud-identity | sncloud_resource_catalog, sncloud_resource_schema, sncloud_identity_read, sncloud_identity_write | Read or manage identity and RBAC resources such as User, ServiceAccount, ServiceAccountBinding, Role, RoleBinding, OIDCProvider, and IdentityPool. |
sncloud_clusters or sncloud-clusters | sncloud_resource_catalog, sncloud_resource_schema, sncloud_clusters_read, sncloud_clusters_write | Read or manage cluster resources such as Instance, PulsarInstance, PulsarCluster, PulsarGateway, and KafkaCluster. |
sncloud_workspaces or sncloud-workspaces | sncloud_resource_catalog, sncloud_resource_schema, sncloud_workspaces_read, sncloud_workspaces_write | Read or manage Workspace resources. |
list and get. Write tools support apply and delete. Write tools accept manifests as JSON strings and support dry_run=true for validation. Use sncloud_resource_catalog to discover supported kinds, then use sncloud_resource_schema to get summary, example, runtime JSON schema, or selected schema paths before writing manifests.
After sncloud_context_use_cluster selects a cluster in a root or organization-level session, sncloud_logs is also available for logs from Functions, Sources, Sinks, and Kafka Connect connectors in the selected cluster. sncloud_logs is cluster-scoped and appears only after cluster selection.
Pulsar clusters support the following tool groups.
| Feature ID | Alias | Description |
|---|
pulsar-admin | | All Pulsar administration tool groups. |
pulsar-admin-topics | topics | List, create, delete, and inspect Pulsar topics. |
pulsar-admin-namespaces | namespaces | List and manage Pulsar namespaces. |
pulsar-admin-namespace-policy | namespace-policy | Get and set namespace-level policies such as retention, TTL, backlog, and anti-affinity namespace lists. |
pulsar-admin-tenants | tenants | List and manage Pulsar tenants. |
pulsar-admin-schemas | schemas | View and manage topic schemas. |
pulsar-admin-subscriptions | subscriptions | List and manage topic subscriptions. |
pulsar-admin-brokers | brokers | List and inspect broker nodes. |
pulsar-admin-brokers-status | brokers-status | Retrieve broker status. |
pulsar-admin-broker-stats | broker-stats | Retrieve broker-level statistics and metrics. |
pulsar-admin-clusters | clusters | List and inspect Pulsar clusters. |
pulsar-admin-functions | functions | List, inspect, and manage Pulsar Functions. |
pulsar-admin-functions-worker | functions-worker | Inspect Functions worker status. |
pulsar-admin-ns-isolation-policy | ns-isolation | Manage namespace isolation policies. |
pulsar-admin-packages | packages | Manage Pulsar packages. |
pulsar-admin-resource-quotas | resource-quotas | View and manage resource quotas. |
pulsar-admin-sinks | sinks | List and manage Pulsar IO sinks. |
pulsar-admin-sources | sources | List and manage Pulsar IO sources. |
pulsar-admin-topic-policy | topic-policy | Get and set topic-level policies. |
pulsar-client | | Produce and consume messages on Pulsar topics. |
| Feature ID | Description |
|---|
kafka-admin | Manage Kafka topics, partitions, and consumer groups. |
kafka-admin-schema-registry | Manage Schema Registry subjects and schemas. |
kafka-client | Produce and consume messages on Kafka topics. |
kafka-admin-kafka-connect | Kafka Connect tools. This feature ID is accepted, but Kafka Connect tools are not exposed on Remote MCP Kafka cluster sessions in the current preview. |
Kafka topic, partition, and consumer-group tools are enabled by kafka-admin.
There are no separate Remote MCP feature IDs named kafka-admin-topics,
kafka-admin-partitions, or kafka-admin-groups.
Combination shortcuts
Use these shortcut IDs to enable multiple tool groups at once.
| Shortcut | Includes |
|---|
all | Every available tool group across Pulsar, Kafka, StreamNative Cloud, and dynamic tools. |
all-pulsar | Pulsar tooling features. |
pulsar | Alias for all-pulsar. |
all-kafka | Kafka tooling features. |
kafka | Alias for all-kafka. |
pulsar-admin | All pulsar-admin-* tool groups. |
kafka-admin | Kafka topic, partition, consumer group, and compatible admin tools. |
cloud | Alias for streamnative-cloud. |
streamnative-cloud | StreamNative Cloud organization tool families. |
| Feature ID | Description |
|---|
functions-as-tools | Expose Pulsar Functions as callable MCP tools on fixed Pulsar cluster sessions. See Functions as Tools. |
agents-as-tools | Accepted dynamic agent-tool feature ID. In the current preview, include functions-as-tools or pulsar-admin-functions when you want to expose eligible Orca agents on fixed Pulsar cluster sessions. See Agents as Tools. |
Dynamic tools are available on fixed cluster endpoints. They are not added
after selecting a cluster inside an organization-level session with
sncloud_context_use_cluster.
- Kafka consume tools use
group for the Kafka consumer group ID. When group is omitted, the server uses an ephemeral group and cannot read committed offsets.
- Pulsar consume tools use
subscription-name for the subscription. This is the Pulsar equivalent of a durable cursor; do not pass a Kafka group parameter to Pulsar tools.
- StreamNative Cloud domain read tools use
operation=list|get, resource, and optional name. name is required for get.
- StreamNative Cloud domain write tools use
operation=apply|delete, resource, and either manifest for apply or name for delete.
- StreamNative Cloud write tools use
manifest as a JSON string. Do not pass YAML or an object. Use dry_run=true for apply before applying changes.
sncloud_logs requires a selected cluster in a root or organization-level session. Use it for logs from Functions, Sources, Sinks, and Kafka Connect connectors.- StreamNative Cloud read tools omit
status and metadata.managedFields unless you set includeStatus=true or includeManagedFields=true.
sncloud_resource_schema defaults to format=summary. Use format=example for an example manifest, format=jsonschema for runtime Kubernetes schema when available, and paths such as spec.broker or spec.clusterRefs to reduce schema size.
Usage tips
- Start minimal. Enable only the tool groups you need. Fewer tools reduce token usage and help AI agents select the right tool more reliably.
- Use shortcuts for broad access. If you need all Pulsar tools, use
all-pulsar instead of listing each group individually.
- Match groups to your cluster type. Pulsar tool groups only work on Pulsar clusters, and Kafka tool groups only work on Kafka clusters. Enabling mismatched groups has no effect.
- Combine groups freely. You can mix StreamNative Cloud, Pulsar, Kafka, and dynamic tool groups. For example,
sncloud_context,pulsar-admin-topics,pulsar-client enables cluster discovery, Pulsar topic administration, and Pulsar message operations.
- Use StreamNative Cloud schema helpers before writes. Call
sncloud_resource_catalog, then sncloud_resource_schema, then a read tool, then a write tool with dry_run=true before applying changes.
