Google Trends inside your assistant. TrendFlow speaks the Model Context Protocol over Streamable HTTP, so any MCP client can use it without installing anything.
https://trendflow.mory.dev/mcp
In Claude Desktop or Cursor, add it as a remote MCP server. In ChatGPT, add it as a connector.
{
"mcpServers": {
"trendflow": { "url": "https://trendflow.mory.dev/mcp" }
}
}| Tool | What it does | Tier |
|---|---|---|
search_topics | Resolve a name to a Google Trends topic id. Call this first. | Free |
get_trending_now | What is surging right now in a country. | Free on rss |
get_interest_over_time | Relative interest for up to 5 terms over a period. | Paid |
get_interest_by_region | Where a term is searched, by country, region, or city. | Paid |
get_related_queries | Top and rising searches related to a term. | Paid |
research_trend | All of the above for one term, in a single call. | Paid |
Topic lookup and the trending RSS feed are free and need no account — they cost nothing to serve, because neither needs a proxy. The tools that query Google's historical endpoints do, so those need a connected TrendFlow account. Your assistant will prompt you to connect one the first time it reaches for them.
Every figure is normalized relative interest, scaled 0–100 within a single result set — never absolute search volume. Results from two separate queries are not comparable to each other.
Responses are cached, from 15 minutes for a one-day series up to 12 hours for multi-year history, which barely moves day to day. If Google rate-limits us we serve a slightly older answer rather than an error.
The MCP server is open source. npx trendflow-mcp speaks stdio, and npx trendflow-mcp --http=8080 serves the same tools over Streamable HTTP. You bring your own proxies — see Proxies and rate limits.