Google Trends MCP Server: Tools, Access and Limits

A Google Trends MCP server lets an AI assistant look up Google Trends data for you: how interest in a term changes over time, where it's popular, and what people search alongside it. MCPifex hosts one with five read-only tools. You need no Google account or key, just an MCPifex API key.

What you can ask it

Once it's connected, you ask about search interest in plain English. For example:

• "Compare interest in Claude Code, Cursor and Copilot over the past year." The AI calls compare_terms.
• "What are people searching for alongside 'MCP server'?" It uses related_queries and shows the top and rising ones.
• "What's trending in Germany today?" It runs trending_now for that country.

The tools

All five tools are read-only and on by default, as of September 2026. There's nothing destructive to leave off.

Scores use Google's relative 0 to 100 index. A 50 means half the interest of the peak, not 50 searches.

What you'll need

Nothing to fill in. This server has no config form, no password and no Google login. Create the instance in the portal, generate an API key, and connect. Test connection calls trending_now to check that everything works. The quickstart walks through the setup.

Limits you should know about

This server reads Google's unofficial Trends endpoints, since Google has no public Trends API. Under load, Google may answer with a 429 (too many requests). The server retries once, then returns a clear error to the AI instead of hanging. That limit comes from Google, not from MCPifex, so if you hit it, wait a bit and ask again.

Scores for rarely searched terms are noisy, so treat one result as a snapshot. Re-run a comparison if it looks off.

Connect your AI app

First create a free account, set up the instance and generate an API key. It starts with mcpx_. Then replace <YOUR_MCPX_KEY> below with your key.

Claude Code

#!/bin/sh
# MCPifex — Claude Code CLI snippet.
# Replace <YOUR_MCPX_KEY> with your MCPifex API key (starts "mcpx_"), from
# the portal's API key page, then run this once from any shell that has the
# `claude` CLI on PATH.
claude mcp add mcpifex --transport http https://mcpifex.com/mcp \
  --header "Authorization: Bearer <YOUR_MCPX_KEY>"

Cursor

Add this to .cursor/mcp.json in your project, or to Cursor's global mcp.json, then reload Cursor:

{
  "mcpServers": {
    "mcpifex": {
      "type": "http",
      "url": "https://mcpifex.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_MCPX_KEY>"
      }
    }
  }
}

Claude Desktop

Use Claude's remote custom connector where it's available. Otherwise, this mcp-remote bridge works, and needs Node.js and npx. Merge the mcpifex entry into the mcpServers object in claude_desktop_config.json, then restart the app:

{
  "mcpServers": {
    "mcpifex": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcpifex.com/mcp",
        "--header",
        "Authorization:${MCPIFEX_AUTH_HEADER}"
      ],
      "env": {
        "MCPIFEX_AUTH_HEADER": "Bearer <YOUR_MCPX_KEY>"
      }
    }
  }
}

ChatGPT

ChatGPT can't send a header, so the key goes in the URL instead: https://mcpifex.com/mcp/<YOUR_MCPX_KEY>. The quickstart has the step-by-step ChatGPT setup. Treat that URL like a password.

Good to know

• Each AI session gets its own isolated server, which stops when the session ends or goes idle.
• Every call is logged in the portal, and revoking a key stops new calls within about a minute.
• Tool calls are unlimited. Plans only limit instances: Free 3, Pro 10, Team 30. See pricing.
• Prefer to query data instead of trends? The PostgreSQL server works the same way.