KOL database: turn gut-feel creator picks into a comparable table

Pipeline

1. Search accounts by niche keyword
   search_creators returns 10 candidates per call with follower count, bio, and verification mark.
2. Pull recent posts and compute median interaction
   Take the last 5 posts with list_creator_posts and compute the median of (likes+comments+shares) — the median resists a single breakout pulling the average.
3. Grid by follower tier × interaction rate
   Mid-sized accounts with high interaction rates are the value tier; large accounts with low interaction rates usually quote above their worth.
4. Store your own snapshots to measure growth
   The API returns a snapshot of the present and offers no historical series. To monitor growth you have to write the numbers into a table yourself every week, deduplicating on the primary key (platform, handle, week).

Real batch result

Endpoints you need

What this article uses search_creators, with the parameters below; use REST when writing code and MCP when wiring a client — both return the same data.

Copy and run

curl -s https://lucydomi.com/mcp/v1/search_creators \
  -H "Authorization: Bearer $BUSYBEE_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"platform": "tiktok", "keyword": "coffee", "limit": 10}'

import os, json, urllib.request

KEY = os.environ["BUSYBEE_API_KEY"]
req = urllib.request.Request(
    "https://lucydomi.com/mcp/v1/search_creators",
    data=json.dumps({"platform": "tiktok", "keyword": "coffee", "limit": 10}).encode(),
    headers={"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"},
    method="POST",
)
data = json.load(urllib.request.urlopen(req, timeout=60))
for it in data["items"]:
    print(it.get("url"), it.get("text", "")[:60])

FAQ

Related reading