Documentation

TrendFlow queries Google Trends — interest over time, interest by region, related queries, and what is trending right now. Use it as a library in Python or JavaScript, over plain HTTP, or as a hosted MCP server inside ChatGPT, Claude, Perplexity, and Cursor.

Choose a language

JSJavaScript

trendflow — 8 guides, from installation to proxy rotation.

Python

trendflow-py — 7 guides, from installation to proxy rotation.

Or use the hosted server

MCP server

Connect ChatGPT, Claude, or Cursor to trendflow.mory.dev/mcp. No install, no proxies to manage.

Perplexity connector

Add TrendFlow as a custom remote connector, and ask Perplexity what is trending.

Google Trends API

There is no official public Trends API. How TrendFlow compares to pytrends and paid SERP APIs.

REST API

Call /api/v1 over plain HTTP with a bearer key — from a backend, a cron job, or another site. Same allowance as the MCP server.

Library reference

Generated from source for both libraries — every class, method, and type.

What the numbers mean

Every figure Google Trends returns is normalized relative interest, scaled 0–100 within a single result set — never an absolute search count. Two separate queries are not comparable to each other. Searching a topic id rather than a literal phrase usually scores far higher, because a topic aggregates every spelling and translation of the same concept.