Skip to content

seed_media_get_artifact

Fetch persisted media by artifact ID as Base64 plus metadata.

Use after the provider URL has expired (2h audio, 24h image/video/3D). Large files cost context; prefer seed_media_export_artifact on stdio.

Requirement Value
Registration Always registered; no provider credentials required.
Execution Foreground only
Required permission artifacts: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 seed_media_get_artifact 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
artifact_id string Yes Artifact ID (ArtifactRef.id) from a generation result.; minLength: 1
Field Type Required Description and constraints
artifact_id string Yes Artifact identifier.
bytes integer Yes Size of the stored content in bytes.
data string Yes Base64-encoded media data.
expires_at string or null No ISO-8601 expiry of the stored artifact, if any.; Default: null
media_type MediaType Yes image, audio, video, or three_d.
mime_type string Yes MIME type of the stored content.
sha256 string Yes SHA-256 hex digest of the stored content.

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.

SeedMediaGetArtifactInput
Field Type Required Description and constraints
artifact_id string Yes Artifact ID (ArtifactRef.id) from a generation result.; minLength: 1
Input schema, including the MCP wrapper
{
"$defs": {
"SeedMediaGetArtifactInput": {
"properties": {
"artifact_id": {
"description": "Artifact ID (ArtifactRef.id) from a generation result.",
"minLength": 1,
"type": "string"
}
},
"required": [
"artifact_id"
],
"type": "object"
}
},
"additionalProperties": false,
"properties": {
"input": {
"$ref": "#/$defs/SeedMediaGetArtifactInput"
}
},
"required": [
"input"
],
"type": "object"
}
Output schema, including nested definitions
{
"$defs": {
"MediaType": {
"description": "Logical generated-media categories.",
"enum": [
"image",
"audio",
"video",
"three_d"
],
"title": "MediaType",
"type": "string"
}
},
"description": "Output model for ``seed_media_get_artifact``.",
"properties": {
"artifact_id": {
"description": "Artifact identifier.",
"title": "Artifact Id",
"type": "string"
},
"bytes": {
"description": "Size of the stored content in bytes.",
"title": "Bytes",
"type": "integer"
},
"data": {
"description": "Base64-encoded media data.",
"title": "Data",
"type": "string"
},
"expires_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "ISO-8601 expiry of the stored artifact, if any.",
"title": "Expires At"
},
"media_type": {
"$ref": "#/$defs/MediaType",
"description": "image, audio, video, or three_d."
},
"mime_type": {
"description": "MIME type of the stored content.",
"title": "Mime Type",
"type": "string"
},
"sha256": {
"description": "SHA-256 hex digest of the stored content.",
"title": "Sha256",
"type": "string"
}
},
"required": [
"artifact_id",
"media_type",
"mime_type",
"sha256",
"bytes",
"data"
],
"title": "SeedMediaGetArtifactOutput",
"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.