Skip to main content
Glama
sjk4425

ncloud-mcp-server

by sjk4425

ncloud_secret_create_secret

Create a Naver Cloud Secret Manager secret from JSON key/value pairs. Set rotation targets and use dryRun=true to preview before creation.

Instructions

Create a secret. secretValue is a JSON object string of 1-100 key/value pairs (≤10,000 bytes); rotationTargets names the keys that rotation replaces. Use dryRun=true to preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memoNoDescription (0-1000 bytes)
dryRunNoIf true, returns a preview without creating
kmsKeyTagNoKMS key tag (see ncloud_secret_list_protection_keys) — required when protectionKeyType=USER_MANAGED_KEY
triggerIdNoRotation trigger ID (see ncloud_secret_list_triggers) — required when autoRotationYN=Y
secretNameYesSecret name (3-15 chars: letters, digits, '-', '_'; starts with a letter)
secretTypeNoSecret type (BASIC is the only valid value)BASIC
secretValueYesSecret value as a JSON object string, e.g. '{"password":"..."}' (1-100 key/value pairs, ≤10,000 bytes)
keyIsolationNoWhich Secret Manager host to call: 'global' (default) for secrets encrypted with a KMS global key (secretmanager.apigw.ntruss.com); 'regional' for secrets encrypted with a KMS region-isolated key (ocapi-kr.ncloud.com/secretmanager — the only option in the JPN region)global
autoRotationYNNoEnable automatic rotation (Y) or not (N, default)N
kmsBoundaryTypeNoKMS key isolation: GLOBAL or ISOLATED (new keys support ISOLATED only)
rotationTargetsYesKeys of secretValue that rotation replaces (at least one)
protectionKeyTypeNoProtection key: DEFAULT (service key) or USER_MANAGED_KEY (your KMS key)DEFAULT
autoRotationPeriodNoRotation period in days (1-730, default 90) — required when autoRotationYN=Y

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations only declare destructiveHint=false, so the description must carry most behavioral burden. It adds that dryRun returns a preview without creating and gives value-size limits — useful beyond the annotation — but omits auth/permission needs, whether creation is immediate, and rotation side effects.

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

Conciseness4/5

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

Three short clauses, front-loaded with the operation and followed by the two most consequential parameter notes. No filler sentences; slightly denser would be ideal but it earns its space.

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

Completeness3/5

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

For a 13-parameter create tool with no output schema and conditional requirements (kmsKeyTag when USER_MANAGED_KEY, triggerId/autoRotationPeriod when autoRotationYN=Y), the description is thin. It does not need to restate return values, but it leaves the conditional-parameter and region/keyIsolation story entirely to the schema.

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 description coverage is 100% and each parameter is richly documented in the schema (including cross-references to list_protection_keys and list_triggers). The description merely restates secretValue and rotationTargets semantics already present in the schema, adding no new meaning, so the baseline 3 applies.

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

Purpose4/5

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

States a clear specific verb+resource ('Create a secret') and immediately adds two parameter-level clarifications. It does not distinguish itself from the many sibling secret tools (e.g. ncloud_secret_update_secret_value, ncloud_secret_job_start), but the core purpose is unambiguous.

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

Usage Guidelines3/5

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

The only usage guidance is 'Use dryRun=true to preview', which is a helpful invocation hint but not when-to-use-vs-alternatives guidance. No mention of prerequisites (KMS key, trigger) or when to prefer the job/stage-based creation flow in siblings.

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