Skip to main content
Glama
sjk4425

ncloud-mcp-server

by sjk4425
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

ncloud_cdss_create_cluster_g3

Create a Kafka cluster on G3 KVM servers by specifying VPC and subnet names and numbers. Use dry-run to preview before provisioning.

Instructions

Create a new CDSS (Kafka) cluster on 3rd-generation KVM servers (G3). ⚠️ Broker node parameters are named dataNode* here, not brokerNode* as in the G2 tool. VPC and subnets must be given by BOTH name and number. Use dryRun=true to preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vpcNoYesVPC number (from ncloud_cdss_get_vpc_list)
dryRunNoPreview without creating
vpcNameYesVPC name — required in addition to vpcNo
clusterNameYesCluster name (3-15 chars: lowercase letters, numbers, '-')
configGroupNoYesConfig group number (from ncloud_cdss_list_config_groups)
dataNodeCountYesBroker node count (3-10, default: 3)
generationCodeYesServer generation code. G3 for 3rd generation
hypervisorCodeYesHypervisor code. KVM for 3rd generation
serverSpecCodeYesServer spec code (from ncloud_cdss_get_server_spec_list, e.g. cdss.s2-g3)
dataNodeSubnetNoYesBroker node subnet number
kafkaVersionCodeYesKafka version code (from ncloud_cdss_get_kafka_versions)
dataNodeSubnetNameYesBroker node subnet name — required in addition to the number
dataNodeProductCodeYesBroker node server type code
dataNodeStorageSizeYesBroker node storage in GB (100-2000, 10GB increments)
managerNodeSubnetNoYesManager node subnet number (from ncloud_cdss_get_subnet_list_g3)
softwareProductCodeYesG3 OS image code (e.g. SW.VCDSS.OS.LNX64.ROCKY.08.G003)
kafkaManagerUserNameYesCMAK access account ID (still required by the API; CMAK itself is being phased out by Ncloud)
managerNodeSubnetNameYesManager node subnet name — required in addition to the number
managerNodeProductCodeYesManager node server type code
dataNodeStorageType2CodeNoBroker storage type. The spec table says NET; the spec page's own sample sends SSD — unresolved, so it is passed through as given
kafkaManagerUserPasswordYesCMAK access account password (still required by the API; CMAK itself is being phased out by Ncloud)
dataNodeStorageInfraResourceDetailTypeCodeNoBroker storage detail type. Documented valid value: CB1

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.16.0
    • changedInput schema / properties / kafkaManagerUserName / description
      Previous value: -"CMAK access account ID"New value: +"CMAK access account ID (still required by the API; CMAK itself is being phased out by Ncloud)"
    • changedInput schema / properties / kafkaManagerUserPassword / description
      Previous value: -"CMAK access account password"New value: +"CMAK access account password (still required by the API; CMAK itself is being phased out by Ncloud)"
  2. Addedv1.15.0

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only indicate destructiveHint=false, so the description carries most of the behavioral burden. It discloses a safe preview path (dryRun=true) and the G3/KVM context, but it does not explain whether real cluster creation is asynchronous, what it returns, or what operational side effects to expect. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each carrying distinct load: what the tool does, the naming pitfall, the dual-identifier requirement, and the dryRun recommendation. The warning marker focuses attention without padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-parameter create tool with no output schema, the description surfaces the three most decision-critical caveats and leaves detailed parameter sourcing to the schema, which is fully described. It could be more complete by noting async behavior or return shape, but nothing an agent needs to avoid a mistaken invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds genuine cross-tool semantics by warning that broker parameters are named dataNode* here and that VPC/subnet identity requires both name and number, which is not inferable from the G2 tool or from individual schema fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a new CDSS (Kafka) cluster', and scopes it to '3rd-generation KVM servers (G3)'. It also distinguishes itself from the G2 sibling by noting the dataNode* naming difference, so an agent can tell it apart from ncloud_cdss_create_cluster without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete invocation guidance: use dryRun=true to preview, supply both VPC and subnet names and numbers, and expect dataNode* rather than brokerNode* as in the G2 tool. It references the G2 alternative but does not explicitly spell out a selection rule between G2 and G3, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools