Competitor monitoring: three numbers a week

Pipeline

1. Fix the list, don't rotate it weekly
   Competitor monitoring pays off through continuity. Pin 5–10 accounts first and write down in plain words who counts as a competitor.
2. Pull recent posts once a week
   Take the last 10 posts with list_creator_posts and store only id, publish time, and likes/comments/shares.
3. Compute three numbers
   ① Median interaction of this week's new posts vs last week (week over week); ② post count (cadence shifts usually show up before the numbers do); ③ breakout rate = the share of posts whose interaction is more than 3x the account's own median.
4. Act only on anomalies
   Interaction down more than 30% week over week, a sudden cadence shift, breakout rate at zero — only these three cases deserve reading post by post.

Real batch result

Endpoints you need

What this article uses list_creator_posts, 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/list_creator_posts \
  -H "Authorization: Bearer $BUSYBEE_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"platform": "tiktok", "creator": "yourcoffeedude", "limit": 10}'

import os, json, urllib.request

KEY = os.environ["BUSYBEE_API_KEY"]
req = urllib.request.Request(
    "https://lucydomi.com/mcp/v1/list_creator_posts",
    data=json.dumps({"platform": "tiktok", "creator": "yourcoffeedude", "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