MCP: Pinterest Trends & Content Intel

Model Context Protocol (MCP) server wrapping pinterest-trends-intel. Gives AI agents four tools for Pinterest trend + content intelligence from logged-out public surfaces - no Pinterest API app review, no login.

Tools

Tool	Args	Returns
search_trends	keywords[], region, include_pins, max_pins_per_query	Trend records: interest trajectory + seasonality (growing/seasonal/evergreen/declining), growth windows, related terms, category.
get_top_pins	query, limit, include_creators	Top pins ranked by engagement + a topic rollup (top creators, category mix, dominant-color palette, top link domains).
get_pin	pin_url	Deep pin record (saves, reactions, comments, engagement score, dominant color, board, creator, outbound domain).
analyze_profile	username	Creator audience signal (follower/following/pin/board counts, monthly views, top boards).

Run modes

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

{ "mode": "call_tool", "tool": "search_trends", "args": { "keywords": ["home office decor"], "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-pinterest-trends-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": "search_trends", "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-pinterest-trends-intel").call(run_input={
    "mode": "call_tool", "tool": "search_trends", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call. The upstream pinterest-trends-intel actor charges its own PPE events (pin_record $0.004, trend_enrichment $0.008, board_audience_signal $0.010) directly to the same run as pass-through. list_tools is free.

Agentic payments (x402 / Skyfire)

This server is x402 (USDC on Base) and Skyfire ready - an AI agent can pay per call with no pre-provisioned API token when the operator enables Apify's MCP monetization. Enable via env: X402_ENABLED + X402_PAY_TO_ADDRESS, and/or SKYFIRE_ENABLED + SKYFIRE_SELLER_ID. The list_tools catalog advertises whichever rails are enabled.

Legal & responsible use

Logged-out public Pinterest surfaces only - no login, no accounts, no paywalls. Creator usernames + aggregate follower counts are public profile facts; no private contact data is collected. See the upstream actor's README for the full responsible-use note.