达人发现：关键词搜账号，批量建库

参数

返回什么

字段与平台无关：帖子类 items[]（url、文案、作者、时间、互动数据、封面），达人类 items[]（handle、昵称、简介、粉丝数、认证），洞察类直接给 sentiment / questions / top_phrases / top_liked / summary。

在 MCP 客户端里怎么用

不需要记参数——把端点加进客户端后，直接用自然语言描述需求，模型会自己挑工具和参数。写代码时再用上面的 REST 形式。

复制即可运行

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": 3}'

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": 3}).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])

真实返回样例

下面这段是线上真实返回（已截断到 1 条，去掉了计费字段）。

{
  "ok": true,
  "platform": "tiktok",
  "tool": "search_creators",
  "count": 1,
  "items": [
    {
      "platform": "tiktok",
      "id": "6746264372110558214",
      "handle": "firedeptcoffee",
      "name": "Fire Department Coffee",
      "bio": "",
      "followers": 1177664,
      "following": 18,
      "posts": 499,
      "verified": true,
      "avatar": "https://p16-common-sign.tiktokcdn-eu.com/tos-maliva-avt-0068/7350822577939415082~tplv-tiktokx-cropcenter-q:100:100:q70.heic?biz_tag=musically_user.user_cover&dr=9606&idc=no1a&ps=87d6e48a&refresh_token=784d15ef&s=SEARCH&sc=avatar&shcp=c1333099&shp=30310797&t=223449c4&x-expires=1792933200&x-signature=KLH1mYPHpaAF%2Firw4ovA2XPf%2Fog%3D",
      "url": "https://www.tiktok.com/@firedeptcoffee"
    }
  ]
}

常见问题

相关内容