MCP: TikTok Research / Content Intel

An MCP server that wraps tiktok-research-intel as six AI-agent tools - delivering the research-equivalent TikTok datasets the gated TikTok Research API gives academics only, to the commercial users it bars (brands, journalists, agencies, analysts) and to AI agents directly.

This server is x402 (USDC on Base) and Skyfire ready: an AI agent can pay per tool call with no pre-provisioned token when the operator enables MCP monetization.

Tools

Tool	Args	Returns
hashtag_trend	hashtag, max_videos, region	Hashtag virality panel: stats, daily time-series, velocity, trend direction, top videos/creators, co-hashtags.
keyword_trend	keyword, max_videos, region	Same panel from TikTok search results.
creator_metrics	creator, max_videos	Creator research profile: followers, engagement distribution, avg ER, posting cadence, engagement trend.
video_engagement	video_url	One video's normalized engagement metrics (views/likes/comments/shares/saves + ER).
comment_sentiment	video_url	Comment-sentiment panel: sentiment + theme tags + positivity rate + top emojis.
sound_trend	hashtag, max_videos, region	Per-sound velocity panels mined from the hashtag's videos.

Modes

• list_tools - emit the tool catalog + agentic-payment descriptor (free).
• call_tool - invoke one tool (tool + args).
• batch - run up to 10 {tool, args} calls in one actor run.

Example

{ "mode": "call_tool", "tool": "hashtag_trend", "args": { "hashtag": "booktok", "max_videos": 50, "region": "US" } }

Connect it to an MCP client

This Actor is exposed as a remote MCP tool through Apify's hosted MCP server. Point any MCP-compatible client (Claude Desktop, Cursor, VS Code, or an OpenAI / LangChain / LlamaIndex agent) at Apify's server with this Actor enabled:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=seibs.co/mcp-tiktok-research-intel",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Get a token (free) from Apify Console -> Settings -> API & Integrations. The Actor then appears as a callable tool. Run mode=list_tools first (free) to fetch every tool's live JSON schema, then call one:

{ "mode": "call_tool", "tool": "hashtag_trend", "args": { } }

Prefer a direct call? Hit the Actor straight through the Apify API / SDK - no MCP client required:

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("seibs.co/mcp-tiktok-research-intel").call(run_input={
    "mode": "call_tool", "tool": "hashtag_trend", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call, plus the upstream tiktok-research-intel PPE pass-through (video_record $0.004, hashtag_trend_enrichment $0.008, comment_sentiment $0.010) billed to the same run. list_tools is free.

Notes

The underlying data is public, logged-out TikTok content; PII is minimized to public creator handles + public engagement metrics. TikTok's comment API is signed and frequently gates logged-out requests, so comment_sentiment can return an empty panel (documented fail-soft). The upstream actor runs on the Playwright image / a warm BROWSER_CDP_URL for the gated surfaces. Use responsibly and in line with TikTok's terms and applicable privacy law.