Skip to main content
Glama
sjk4425

ncloud-mcp-server

by sjk4425
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

ncloud_cdss_create_cluster

Create a new CDSS Kafka cluster on Naver Cloud Platform. Use dryRun to preview or returnClusterId to retrieve the new cluster's ID directly.

Instructions

Create a new CDSS (Kafka) cluster (G2). Set returnClusterId=true to get the new cluster's serviceGroupInstanceNo back — the default operation returns only success/failure, so you would otherwise have to find the cluster with ncloud_cdss_list_clusters. Use dryRun=true to preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vpcNoYesVPC number
dryRunNoPreview without creating
clusterNameYesCluster name (3-15 chars, lowercase+numbers+'-')
configGroupNoYesConfig group number
brokerNodeCountYesNumber of broker nodes (3-10)
returnClusterIdNoIf true, calls the variant that returns the new cluster's serviceGroupInstanceNo
kafkaVersionCodeYesKafka version code (from get_kafka_versions)
brokerNodeSubnetNoYesBroker node subnet number
managerNodeSubnetNoYesManager node subnet number
softwareProductCodeYesOS type code (from get_os_products)
kafkaManagerUserNameYesCMAK access account ID (still required by the API; CMAK itself is being phased out by Ncloud)
brokerNodeProductCodeYesBroker node server type code
brokerNodeStorageSizeYesBroker storage in GB (100-2000, 10GB increment)
managerNodeProductCodeYesManager node server type code
kafkaManagerUserPasswordYesCMAK access account password (still required by the API; CMAK itself is being phased out by Ncloud)

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. Changed1 schema field changedv1.15.0
    • addedInput schema / properties / returnClusterId
      Added value: +{
+  "default": false,
+  "description": "If true, calls the variant that returns the new cluster's serviceGroupInstanceNo",
+  "type": "boolean"
+}
  3. First observedv1.10.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only include destructiveHint=false, so the description carries the burden of explaining the operation's behavior. It discloses that the default returns only success/failure, while setting returnClusterId=true yields the new cluster's serviceGroupInstanceNo — key behavioral detail that affects how the agent should interpret results. It does not cover other potential side effects (e.g., costs, idempotency), but for a create operation with this scope, it adds sufficient clarity beyond the annotations.

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?

The description is two sentences, with the core action front-loaded and the optional behaviors (returnClusterId, dryRun) concisely explained. There is no redundant phrasing or unnecessary detail; every sentence earns its place by guiding the agent's invocation.

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?

Given the tool's complexity (15 parameters, 13 required, no output schema), the description effectively covers the key decision points: how to obtain the cluster ID and how to preview without creating. It also hints at the need to fetch certain codes (e.g., kafkaVersionCode from get_kafka_versions, softwareProductCode from get_os_products) via the schema, but does not elaborate on all possible inputs. Overall, it is sufficiently complete for an agent to call it correctly, though a note on required prerequisite lookups could strengthen it further.

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

Parameters3/5

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

Schema coverage is 100%, so all parameters already have descriptions in the input schema, including the behavior of returnClusterId and dryRun. The description adds marginal value by emphasizing the alternative of using ncloud_cdss_list_clusters when returnClusterId is false, but it does not enrich the meaning of most parameters beyond what the schema provides. This meets the baseline for high schema coverage.

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 states 'Create a new CDSS (Kafka) cluster (G2)' — a specific verb, resource, and generation. It distinguishes from the sibling ncloud_cdss_create_cluster_g3 by explicitly labeling this as G2, and clarifies the default behavior versus returnClusterId=true, leaving no ambiguity about what the tool does.

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?

The description explains when to use returnClusterId=true and dryRun=true, and notes that otherwise you must find the cluster with ncloud_cdss_list_clusters. It does not explicitly contraindicate using this for G3, but the (G2) label and naming sufficiently differentiate it from the G3 variant for an agent to pick the correct sibling.

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