Extract and repurpose content

Extract source text, verify completion, and separate source extraction from media generation and publication.

Prompt for your assistant:

Extract the content from this source with Blotato, then adapt it for the social platforms I choose. If a platform needs media, use media I supply or generate a visual before publishing.

Before starting

Use an authenticated connection. Choose sourceType explicitly. Use text for text or perplexity-query, and url for article, YouTube, Twitter/X, TikTok, audio, or PDF sources. A URL alone does not choose the source type.

MCP example

1. Call blotato_create_source with the user's source. This example uses supplied text and requires no external source URL.

{
  "sourceType": "text",
  "text": "Our workshop opens on October 15. Registration closes on October 10."
}

1. Save the returned id. The tool waits internally for up to 20 seconds. If the result is still queued or processing, call blotato_get_source_status with this shape, replacing the example ID.

{"id": "123e4567-e89b-12d3-a456-426614174000"}

REST equivalent

Send the following body to POST https://backend.blotato.com/v2/source-resolutions-v3 with blotato-api-key: YOUR_API_KEY and Content-Type: application/json. REST nests the source fields. MCP does not.

{
  "source": {
    "sourceType": "text",
    "text": "Our workshop opens on October 15. Registration closes on October 10."
  }
}

A 201 response contains the job ID, not extracted content:

{"id": "123e4567-e89b-12d3-a456-426614174000"}

Read GET /v2/source-resolutions-v3/123e4567-e89b-12d3-a456-426614174000 with the same authentication header. A completed response has this shape. The title and content below are illustrative, not guaranteed output text.

{
  "id": "123e4567-e89b-12d3-a456-426614174000",
  "status": "completed",
  "title": "Workshop dates",
  "content": "Our workshop opens on October 15. Registration closes on October 10."
}

Completion and recovery

1. Wait at least 10 seconds between status requests for an unfinished job. Use a bounded wait, such as 2 minutes, then report the saved ID and pending state. This is a client wait budget, not a service completion promise.

2. On completed, use the returned content and title. Do not treat an accepted ID as extracted content. If MCP content ends with [output truncated], it is not the full extraction. Use the REST lookup with the same ID when your client has an authorized API connection, or disclose the incomplete content. Repeated MCP lookups do not paginate the text.

3. On REST or MCP status lookup failed, inspect message. The MCP create tool reports extraction failure through isError with the source ID, while the status tool returns a failed status in its JSON result. Check both the tool error flag and the operation status. Correct the source or access problem before another extraction attempt.

4. After a timeout, look up the saved ID instead of submitting another extraction. If no ID was received, report the uncertain outcome before retrying.

5. Adapt the content to the user's request. Stop after returning the content for an extraction-only request. For publication, use existing media, or omit media for text-only posts supported by the selected platform. Create a visual only when new media is requested. Follow Publish and verify with the user's publication approval.

Extraction produces source content. It does not itself download a reusable social video or publish a post. An Instagram caption without an image or video is insufficient for publishing.

See Create Source and Get Source for source-specific requirements and errors.