What should I do if I hit a Google Trends 429 rate limit?
The server has built-in 1–3 second random delays and backoff retries. If you still hit limits, reduce call frequency, set an HTTPS proxy, or switch to the `trendspy` provider.
@Eason-Gao3
基本情報
A production-grade Google Trends MCP server for AI workflow integration. Supports batch research of up to 50 keywords with cross-batch normalization, compare up to 5 keywords precisely, async task support, and REST API + GPT Actions. Compatible with 7 major AI clients: Claude Des
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"google-trends": {
"url": "https://easontrendmcp.dpdns.org/mcp",
"headers": {
"Authorization": "Bearer gtmcp_live_your-api-key"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
このサーバーは認証が必要です。ツールの取得にはログインや提供元の認証情報が必要な場合があります。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
Google Trends MCP is a Model Context Protocol server that gives AI assistants structured Google Trends data. It supports batch keyword research (up to 50 keywords per batch), cross-batch normalization for comparability, and production-level SaaS deployment. Built with FastMCP, it works with Claude Desktop, ChatGPT, Cursor, Perplexity, and other major AI clients.
Install Python 3.11+, clone the repo, create a virtual environment, install dependencies, then run python server.py for local stdio mode. For a web service, use --transport streamable-http with host and port. Deploy publicly with Docker Compose. Configure client MCP entries with the endpoint URL and an API key (obtained from the dashboard after Google OAuth login).
compare_keywords, research_keywords, research_keywords_async, get_research_taskThe server has built-in 1–3 second random delays and backoff retries. If you still hit limits, reduce call frequency, set an HTTPS proxy, or switch to the `trendspy` provider.
In stdio mode, `stdout` carries MCP JSON-RPC protocol messages; ordinary text would break the protocol. Logs must be written to `stderr`. Only `--smoke-test` mode allows JSON output to stdout.
`compare_keywords` returns raw Google Trends batch-relative scores for up to 5 keywords. `research_keywords` returns cross-batch normalized estimates using an anchor keyword, suitable for directional research across many keywords.
With 2–4 concurrent threads and random delays, 10 keywords take about 5–10 seconds; 50 keywords take about 15–30 seconds. In-process caching (default 15 minutes) skips network calls for repeated requests.
When `GOOGLE_CLIENT_ID` is not set, the server enters dev mode. Visit `/auth/dev-login` to log in with a virtual account — no Google account needed.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
Hindsight: Agent Memory That Learns
Open-source MCP to use Blender with any LLM

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
コメント