TikTok data for AI agents
Creator profiles, video stats and keyword search across videos and accounts, as structured JSON. One key, no TikTok developer program to apply to.
Copy the setup prompt.
Your agent does the rest.
Connect the superagnt MCP server at https://mcp.superagnt.com/mcp/tiktok to this agent for me (I'll sign in through my browser). The setup guide for each kind of agent is at https://www.superagnt.com/install?facet=tiktok» a new workspace starts with the TikTok tools already on. On an existing workspace, your agent switches them on during setup.
Everything your agent can pull
Public creator details by username: follower and following counts, total likes, video count, bio and verification.
Every video on an account, with a continuation token so an agent can page back through the whole history.
One video by id with play, like, comment and share counts, plus description, sound and author.
Keyword search across videos, which is the surface a trend-watching agent needs to see what is being posted right now.
Keyword search across accounts, for finding creators in a niche instead of starting from a handle you already know.
Videos inside a creator collection, useful when a brand groups its catalogue on-profile.
tool names07as your agent sees them
data_tiktok_video_detailsdata_tiktok_user_s_videosdata_tiktok_collection_videos_detailsdata_tiktok_user_s_videos_continuationdata_tiktok_user_s_detailsdata_tiktok_search_accountsdata_tiktok_search_videosThree jobs it can start on today
Influencer shortlist from a keyword
The agent searches videos for your product category, collects the creators behind the top results, pulls each profile, and ranks them on median views per video rather than follower count.
Trend watch on a schedule
A cron schedule runs a video search every few hours, writes new videos to the workspace database, and pings Slack when a sound or format crosses a threshold you set.
Post-campaign reporting
After a creator drop, the agent walks each creator feed, finds the sponsored videos, and reports views, likes and comments per post against what you paid.
What comes back
Your agent reads this response directly, with no parsing layer of your own in between. The same JSON comes back over plain HTTP, so a cron job or a script sees exactly what the agent sees.
https://mcp.superagnt.com/mcptool calldata_tiktok_user_s_details{
"username": "northloopcoffee"
}{
"user": {
"id": "7100000000000000001",
"username": "northloopcoffee",
"nickname": "North Loop Coffee",
"verified": false,
"follower_count": 128400,
"following_count": 87,
"video_count": 412,
"heart_count": 2140000
},
"...": "signature, avatar urls, region"
}What it costs to run
deducted from your credit balance
Every call in TikTok costs the same, and only a successful call is billed.
One balance covers this source and every other one, so there is no per-source subscription and no upstream account of your own to keep alive.
how credits work →Before you wire it up
01Do I need TikTok API access?
No. There is no developer application, no app review and no OAuth. One key and one credit balance cover it.
02How does my agent get these tools?
Connect your MCP client to https://mcp.superagnt.com/mcp. A server created now serves these tools by default. On an older server, have the agent call agnt_tools_enable with the family id data:tiktok and they appear in its next tools/list.
03Can it page through an entire account?
Yes. data_tiktok_user_s_videos returns a continuation token. Feed it to data_tiktok_user_s_videos_continuation and keep going until no token comes back.
04How is usage billed?
Calls consume platform credits based on provider and endpoint. See credit costs in the dashboard and on each endpoint page.
05What about rate limits?
Rate limits depend on your plan. The API returns standard HTTP status codes; retry with backoff on 429 responses.
Point your client at https://mcp.superagnt.com/mcp and your agent has this, plus everything else on one balance.