Creator vetting

Give a clear yes, no or "ask for more data" on one creator, with the evidence.

Steps

1. Profile: tiktok_profile, instagram_profile or youtube_channel with the handle.
2. Last 20 to 30 posts: tiktok_profile_videos, instagram_user_posts or youtube_channel_videos. Page once if the first page has fewer than 20.
3. Compute:
   • median plays and view rate (median plays / followers). Healthy short-video accounts are usually above 5%; under 1% is a red flag.
   • engagement rate (likes + comments) / plays. Very high likes with very few comments suggests bought likes.
   • spread: one viral post and the rest flat means the follower count overstates reach. Report the median, not the mean.
   • posting cadence and the date of the last post.
   • share of posts marked is_ad, if present.
4. Comment sample: pull comments on 2 recent posts (tiktok_comments, instagram_comments, youtube_comments, by url). Look for generic bot comments ("nice", emoji only, repeated text from many accounts) and for what the audience actually talks about.
5. Brand safety: skim captions and transcripts of the 5 most viewed posts (tiktok_transcript, instagram_transcript, youtube_transcript) for topics the brand would not want.
6. Optional, TikTok only: /v1/tiktok/user/audience (handle) returns audience demographics; it costs up to 26 credits, so ask first.

Output

Verdict first (Go, No go, or Ask for their analytics), then a short evidence table: followers, median plays, view rate, engagement rate, comment quality, last post, red flags. Link the posts you looked at.

Cost

About 5 to 8 credits per creator, plus up to 26 for audience demographics.

How to call ScrapeIO

Needs SCRAPEIO_API_KEY. If it is missing, ask the user to get a free key at https://scrapeio.com/login (100 credits, no card). Never print the key.

• With the scrapeio MCP server: use the named tool when it exists (for example tiktok_profile). For any other path, use call_endpoint with { "path": "/v1/...", "params": { ... } }.
• Without MCP: curl -s "https://scrapeio.com<path>?<params>" -H "x-api-key: $SCRAPEIO_API_KEY".
• Answers are in data; lists are data.items with data.cursor and data.has_more. Fields are the same on every platform: handle, followers, plays, likes, comments, shares, created_at, url.
• 403 (private) and 404 (not found) are free: skip and move on. Retry 502 once. 402 means the user needs credits (https://scrapeio.com/pricing).
• Watch credits_remaining and tell the user before a step would spend more than they expect.