ncloud-mcp-server

ncloud_cdss_change_kafka_config

Idempotent

Replace a Kafka config group's entire custom configuration, reverting omitted settings to defaults. To keep a value, send it; then re-apply the group to make changes effective.

Instructions

⚠️ Replaces the Config Group's ENTIRE custom configuration. Any setting you omit loses its custom value and reverts to the default — the API reports SUCCESS either way, so the revert is silent. Read the current values with ncloud_cdss_get_kafka_config and send EVERY value you want to keep, not just the ones you are changing. Named settings are typed parameters; anything without one goes in additionalSettings. range in the read response gives each setting's valid bounds (the server enforces them), and modifyYn: false marks settings the server silently discards rather than rejecting (authorizer.class.name is one). The group must be re-applied to a cluster with ncloud_cdss_apply_config_group for a change to take effect.

Input Schema

TableJSON Schema

Name	Required	Description
`numIoThreads`	No	num.io.threads
`configGroupNo`	Yes	Config group number (from ncloud_cdss_list_config_groups)
`numPartitions`	No	num.partitions
`logSegmentBytes`	No	log.segment.bytes (e.g. 1073741824)
`kafkaVersionCode`	Yes	Kafka version code of the group (from ncloud_cdss_get_kafka_versions)
`logCleanerEnable`	No	log.cleaner.enable
`logCleanupPolicy`	No	log.cleanup.policy (e.g. 'delete', 'compact')
`deleteTopicEnable`	No	delete.topic.enable
`logCleanerThreads`	No	log.cleaner.threads
`logRetentionBytes`	No	log.retention.bytes (-1 for unlimited)
`logRetentionHours`	No	log.retention.hours (e.g. 168)
`numNetworkThreads`	No	num.network.threads
`additionalSettings`	No	Settings without a named parameter above — sent as additionalKafkaConfigGroupDetailList. ⚠️ Value application is unverified: an earlier attempt registered the entry with an empty value
`authorizerClassName`	No	authorizer.class.name. ⚠️ Read-only in practice: the server accepts this, answers SUCCESS, and discards it (modifyYn=false)
`autoCreateTopicsEnable`	No	auto.create.topics.enable
`logFlushIntervalMessages`	No	log.flush.interval.messages
`allowEveryoneIfNoAclFound`	No	allow.everyone.if.no.acl.found
`offsetsTopicReplicationFactor`	No	offsets.topic.replication.factor

Schema Changelog

Changes observed during successful MCP inspections.

Changed20 schema fields changedv1.15.0Sep 20, 2026

addedInput schema / properties / additionalSettings

Added value: +{
+  "description": "Settings without a named parameter above — sent as additionalKafkaConfigGroupDetailList. ⚠️ Value application is unverified: an earlier attempt registered the entry with an empty value",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "configName": {
+        "description": "Kafka setting name (e.g. 'compression.type')",
+        "type": "string"
+      },
+      "configValue": {
+        "description": "Value to set, as a string",
+        "type": "string"
+      }
+    },
+    "required": [
+      "configName",
+      "configValue"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / allowEveryoneIfNoAclFound

Added value: +{
+  "description": "allow.everyone.if.no.acl.found",
+  "type": "boolean"
+}

addedInput schema / properties / authorizerClassName

Added value: +{
+  "description": "authorizer.class.name. ⚠️ Read-only in practice: the server accepts this, answers SUCCESS, and discards it (modifyYn=false)",
+  "type": "string"
+}

addedInput schema / properties / autoCreateTopicsEnable

Added value: +{
+  "description": "auto.create.topics.enable",
+  "type": "boolean"
+}

changedInput schema / properties / configGroupNo / description

Previous value: -"Config group number"New value: +"Config group number (from ncloud_cdss_list_config_groups)"

addedInput schema / properties / deleteTopicEnable

Added value: +{
+  "description": "delete.topic.enable",
+  "type": "boolean"
+}

removedInput schema / properties / kafkaConfig

Removed value: -{
-  "additionalProperties": {
-    "type": "string"
-  },
-  "description": "Kafka config key-value pairs to change",
-  "type": "object"
-}

addedInput schema / properties / kafkaVersionCode

Added value: +{
+  "description": "Kafka version code of the group (from ncloud_cdss_get_kafka_versions)",
+  "type": "number"
+}

addedInput schema / properties / logCleanerEnable

Added value: +{
+  "description": "log.cleaner.enable",
+  "type": "boolean"
+}

addedInput schema / properties / logCleanerThreads

Added value: +{
+  "description": "log.cleaner.threads",
+  "type": "number"
+}

addedInput schema / properties / logCleanupPolicy

Added value: +{
+  "description": "log.cleanup.policy (e.g. 'delete', 'compact')",
+  "type": "string"
+}

addedInput schema / properties / logFlushIntervalMessages

Added value: +{
+  "description": "log.flush.interval.messages",
+  "type": "number"
+}

addedInput schema / properties / logRetentionBytes

Added value: +{
+  "description": "log.retention.bytes (-1 for unlimited)",
+  "type": "number"
+}

addedInput schema / properties / logRetentionHours

Added value: +{
+  "description": "log.retention.hours (e.g. 168)",
+  "type": "number"
+}

addedInput schema / properties / logSegmentBytes

Added value: +{
+  "description": "log.segment.bytes (e.g. 1073741824)",
+  "type": "number"
+}

addedInput schema / properties / numIoThreads

Added value: +{
+  "description": "num.io.threads",
+  "type": "number"
+}

addedInput schema / properties / numNetworkThreads

Added value: +{
+  "description": "num.network.threads",
+  "type": "number"
+}

addedInput schema / properties / numPartitions

Added value: +{
+  "description": "num.partitions",
+  "type": "number"
+}

addedInput schema / properties / offsetsTopicReplicationFactor

Added value: +{
+  "description": "offsets.topic.replication.factor",
+  "type": "number"
+}

changedInput schema / required

Previous value: -[
-  "configGroupNo",
-  "kafkaConfig"
-]New value: +[
+  "configGroupNo",
+  "kafkaVersionCode"
+]

First observedv1.10.1Jul 29, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the idempotentHint=true and destructiveHint=false annotations, the description reveals critical behavioral traps: omitted settings silently revert to defaults, the API reports SUCCESS even when reverting, the server enforces bounds from `range`, and `modifyYn: false` settings are silently discarded rather than rejected. This is precisely the kind of non-obvious behavior that could cause data loss if undisclosed. No contradiction with the annotations is present (mutating config isn't the same as destroying the resource).

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 dense but contains zero filler — every sentence carries distinct, load-bearing information: replacement semantics, silent success, read-first instruction, parameter routing, bounds enforcement, silent-discard behavior, and the required apply step. The most critical warning (entire-config replacement) is front-loaded, and the two ⚠️ markers flag the highest-risk behaviors.

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

Completeness5/5

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

For a complex 18-parameter mutation tool with no output schema, the description covers every decision an agent needs to make correctly: which values to send (all of them), how to obtain them (from get_kafka_config), how to classify each setting (named vs additionalSettings), which settings won't take effect (modifyYn: false), and what post-step is required (apply_config_group). No critical usage information 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 coverage is 100%, so parameters are individually documented, but the description adds genuinely useful structure: 'Named settings are typed parameters; anything without one goes in additionalSettings' explains how the 18 parameters route to the API. It also flags authorizerClassName as effectively read-only despite appearing settable, and explains how the read response's `range`/`modifyYn` fields relate to parameter validity. This exceeds the baseline for fully-covered schemas.

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 statement: 'Replaces the Config Group's ENTIRE custom configuration.' This precisely defines both what the tool does and the scope of its effect. It also names sibling tools (ncloud_cdss_get_kafka_config, ncloud_cdss_apply_config_group), so an agent can distinguish this mutation from related read/apply operations without opening their schemas.

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

Usage Guidelines5/5

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

The description gives an explicit read-before-write workflow: 'Read the current values with ncloud_cdss_get_kafka_config and send EVERY value you want to keep.' It also states the required follow-up action ('must be re-applied to a cluster with ncloud_cdss_apply_config_group for a change to take effect'), telling the agent exactly when this tool fits in a multi-step sequence and which siblings to use around it.

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

Deploy Server

ncloud_cdss_change_kafka_config

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools