MCP: TikTok Trending Products - Product, Video & Price Feed

An MCP server wrapping seibs.co/tiktok-trending-products. It gives AI agents three tools for pulling a public trending-TikTok-Shop-products feed - the product, the video driving it, and its price/sales - with no seller account, no TikTok Shop API, no data-security review.

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

Tools

Tool	What it returns
trending_products	The full feed for a region + window: each product with rank, category, price + sale price, "X sold", rating, the driving video (creator + URL + embed + views), and a buy link.
discover_products	Cheap reconnaissance: the trending leaderboard only (rank / product / category / trend), no price or video enrichment.
trending_in_category	The feed filtered to one category (substring match, e.g. Beauty, Home, Health).

Usage

This actor speaks the portfolio's MCP-over-actor protocol: a run with mode = list_tools, call_tool, or batch.

Discover the tools (free):

{ "mode": "list_tools" }

Call one tool:

{
  "mode": "call_tool",
  "tool": "trending_products",
  "args": { "region": "US", "period_days": 7, "max_products": 20 }
}

Get what's hot in a category:

{
  "mode": "call_tool",
  "tool": "trending_in_category",
  "args": { "category": "Beauty", "region": "US" }
}

Batch several calls (max 10):

{
  "mode": "batch",
  "calls": [
    { "tool": "trending_products", "args": { "region": "US" } },
    { "tool": "trending_in_category", "args": { "category": "Home" } }
  ]
}

Every tool returns a uniform envelope: { tool, args, ok, count, items, summary, error }. Tools never throw - an upstream failure becomes ok: false with an error string.

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-trending-products",
      "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": "trending_products", "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-trending-products").call(run_input={
    "mode": "call_tool", "tool": "trending_products", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call, plus the upstream actor's pass-through PPE (trending_product $0.005, enriched_product $0.005) billed to the same run. list_tools is free. A tool call that returns nothing still bills the flat fee for the dispatch; upstream charges only fire on real records.

What it's for

• Trend sites (e.g. a daily-virals feed): let an agent refresh "today's trending products + videos" on demand.
• Affiliates / dropshippers: ask "what's trending in Beauty this week" and get products + the videos driving them + buy links.
• AI pipelines: a clean, typed tool surface over the public TikTok trending-commerce data - no scraping code, no seller credentials.

See the upstream actor for the full feed schema, velocity/price-history (on scheduled runs), and how to power a website from the dataset.