Skip to content

ark_moderation_get

Look up media block reasons for Seedance 2.0/2.5 or material assets.

Requires AK/SK, Advanced Creation Rights, whitelist activation and IAM GetModerationResult. Trusted local/loopback access, account-wide and not tenant-isolated. Shared HTTP keys lack moderation:read. Records: within 14 days and after whitelist activation. Images/video/audio, not text. Seedance 2.5: use task_id, not request_id. No automatic retries or background jobs. Ten queries/minute per server runtime. Not found or empty reasons never establish approval or safety.

Requirement Value
Registration Requires BYTEPLUS_MODELARK_MODERATION_ENABLED=true, BYTEPLUS_MODELARK_ACCESS_KEY and BYTEPLUS_MODELARK_SECRET_KEY. Provider whitelist and Advanced Creation Rights required; configuration does not verify entitlement. Denied to shared HTTP key holders.
Execution Foreground only
Required permission moderation:read

This site lists the full configured capability surface, not the tools enabled on your particular server. Use model discovery and job discovery to check your connection. Credentials are server configuration, never tool arguments.

Ask your connected AI client to use ark_moderation_get for the operation you want. The client constructs the arguments and handles tool calls. Review its proposed operation before approving anything billable. For a non-billable introduction, start with discovery without generation.

Call this tool directly. It is not a background-job target.

Match the input fields below and the full JSON Schema. See the worked examples for this capability and Background Execution for job/result handling.

The MCP arguments object wraps these fields as {"input": {...}}.

Field Type Required Description and constraints
id string Yes Bare provider task, asset, or inference request ID; not an Ark job ID or asset:// URI.; minLength: 1; maxLength: 256
type “task_id”, “asset_id”, “request_id” Yes ID type: task_id, asset_id, or request_id. Seedance 2.5 request_id lookup is unsupported; use task_id.
Field Type Required Description and constraints
block_reasons array of ModerationBlockReason Yes Provider-reported block reasons. An empty list does not establish approval or safety.
id string Yes The queried provider ID, not the lookup’s diagnostic request ID.
type “task_id”, “asset_id”, “request_id” Yes Whether id identifies a task, asset, or request.

Field types named above refer to these shared definitions. Optional/null fields, enum choices and bounds are retained in the complete schemas below. Schema validation is followed by runtime capability and security checks.

ModerationGetInput
Field Type Required Description and constraints
id string Yes Bare provider task, asset, or inference request ID; not an Ark job ID or asset:// URI.; minLength: 1; maxLength: 256
type “task_id”, “asset_id”, “request_id” Yes ID type: task_id, asset_id, or request_id. Seedance 2.5 request_id lookup is unsupported; use task_id.
Input schema, including the MCP wrapper
{
"$defs": {
"ModerationGetInput": {
"additionalProperties": false,
"description": "One explicit provider-record lookup.",
"properties": {
"id": {
"description": "Bare provider task, asset, or inference request ID; not an Ark job ID or asset:// URI.",
"maxLength": 256,
"minLength": 1,
"type": "string"
},
"type": {
"description": "ID type: task_id, asset_id, or request_id. Seedance 2.5 request_id lookup is unsupported; use task_id.",
"enum": [
"task_id",
"asset_id",
"request_id"
],
"type": "string"
}
},
"required": [
"id",
"type"
],
"type": "object"
}
},
"additionalProperties": false,
"properties": {
"input": {
"$ref": "#/$defs/ModerationGetInput"
}
},
"required": [
"input"
],
"type": "object"
}
Output schema, including nested definitions
{
"$defs": {
"ModerationBlockReason": {
"description": "One provider-reported classification, not an independent safety finding.",
"properties": {
"detail": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Provider explanation when available; may be absent, null, or empty.",
"title": "Detail"
},
"label": {
"description": "Provider category: Safety, Copyright, Celebrity, Deepfake, or a new label.",
"minLength": 1,
"title": "Label",
"type": "string"
},
"sub_label": {
"description": "Provider subcategory, preserved without interpretation.",
"title": "Sub Label",
"type": "string"
}
},
"required": [
"label",
"sub_label"
],
"title": "ModerationBlockReason",
"type": "object"
}
},
"description": "Block reasons for one existing provider record.",
"properties": {
"block_reasons": {
"description": "Provider-reported block reasons. An empty list does not establish approval or safety.",
"items": {
"$ref": "#/$defs/ModerationBlockReason"
},
"title": "Block Reasons",
"type": "array"
},
"id": {
"description": "The queried provider ID, not the lookup's diagnostic request ID.",
"title": "Id",
"type": "string"
},
"type": {
"description": "Whether id identifies a task, asset, or request.",
"enum": [
"task_id",
"asset_id",
"request_id"
],
"title": "Type",
"type": "string"
}
},
"required": [
"id",
"type",
"block_reasons"
],
"title": "ModerationResult",
"type": "object"
}
  • Missing tool: check provider credentials and feature flags, then restart the connection.
  • Invalid arguments: keep the correct wrapper and follow current model limits from discovery. A valid schema alone does not prove the chosen model supports the combination.
  • A job completes with an error: inspect the original tool result, not only the outer job status. Never automatically resubmit potentially billable work.
  • Local output writes from jobs require server-configured OUTPUT_ROOTS; HTTP cannot write to a client’s local disk.

See configuration, background execution, and artifact delivery.