Perplexity reaches the Trends API MCP server through its connector settings. Add a custom connector with the URL https://trendsapi.ai/mcp, sign in on Trends API to authorize, and the three tools join the answer stack: get_time_series for keyword history, get_growth for percent change over preset windows, and get_top_trends for live boards. The authorized key is the same product key as the REST API. Server-level detail sits on MCP server setup.

Add the connector in Perplexity

Open connector settings and add a custom remote MCP connector. Name: Trends API. Server URL: https://trendsapi.ai/mcp. The quickstart on the homepage opens the same flow with the fields filled in. Complete the sign-in on Trends API, then start a new thread so the tool list loads. Nothing is installed locally, and no config file is edited in this flow.

What changes in an answer

A Perplexity answer without the connector can describe a trend from articles. With the connector it can measure one. "Is interest in heat pumps rising" becomes a get_growth call on google search over 12M, and the reply quotes the percent next to the sources it read. "What is on the TikTok board" becomes get_top_trends with type TikTok Trending Hashtags.

History calls take a source string. Board calls take a type label. The full list sits on the sources reference, and naming the platform in the question removes the mapping guess.

Chat answers versus stored data

Perplexity is a reading surface. The reply is prose with numbers in it, which suits a briefing or a quick check before a meeting. A pipeline that stores rows belongs on POST https://api.trendsapi.ai/api, where the reply is JSON a job can write to a table. Only successful 200 responses count against quota; caps sit on pricing. The Gemini CLI version of this setup sits on Gemini Trends MCP.