HasData/google-trends-mcp

A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf and any other MCP client one Google Trends tool. Pull interest over time, interest by region, and the rising and top related queries and topics for any term, all as structured JSON, with no scraping library to keep alive and no Google account.
**1,000 free credits every month, no card required**, which is 100 Google Trends calls.
- Prompts and resources
Contents
- What you need
- Quick start
- Example prompts
- Tools
- Errors and failure paths
- Pricing, free tier and limits
- Tool selection
- How it compares
- FAQ
- HasData links
- Development
- Contributing
- License
What you need
An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers about 100 calls a month at the 10-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run and no Google account anywhere in the flow. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/google-trends-mcp on npm and hasdata-google-trends-mcp on PyPI, shown below.
Quick start
The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.
| Field | Value |
| :--- | :--- |
| URL | https://mcp.hasdata.com/mcp?apis=google_trends |
| Transport | HTTP, streamable |
| Auth header | x-api-key: HASDATA_API_KEY |
Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.
Claude Code
Claude Desktop
Settings, then Connectors, then Add custom connector, then paste https://mcp.hasdata.com/mcp?apis=google_trends and sign in.
For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The @hasdata/google-trends-mcp package is that launcher, and it reads the key from the environment. Add this to claude_desktop_config.json:
For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:
Cursor
~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:
Windsurf
~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:
VS Code
.vscode/mcp.json in the workspace:
Example prompts
Prompts, not code. Paste one in and the agent picks the tool itself. Each is annotated with the calls it takes, because every successful call costs 10 credits.
> Chart interest in "cold brew coffee" in the US over the past 12 months and tell me which weeks it peaked.
*One call, 10 credits. The weekly series comes back in a single request.*
> For "cold brew coffee" in the US, give me the rising related queries and flag the ones marked Breakout.
*One call, 10 credits.*
> Compare interest in "cold brew" against "iced coffee" worldwide over five years and say which one is growing.
*One call, 10 credits. The tool takes several terms in one timeseries request.*
> Show me interest in "sunscreen" by US state over the past 90 days so I can see where demand is highest.
*One call, 10 credits. This is the interest-by-region view at state granularity.*
A comparison across terms rides in one timeseries call. Region breakdowns, related queries and related topics are each their own dataType, so a prompt that wants a chart plus its rising queries is two calls.
Tools
| Tool | What it returns |
| --- | --- |
| hasdata_google_trends_search_getTrendsData | Interest-over-time series, geo-level breakdowns, and rising/top related topics/queries with relative scores. 10 credits a call |
One tool, read-only. The sample below is trimmed from a real call, and the numbers move as the trend moves. Read it as a shape. The tool name links to its endpoint reference, which carries the full parameter list.
The sample is the payload, not the whole response. A tools/call result carries one text block, and that text is itself JSON holding url, status, text and json, with the scraped data under json. From a raw JSON-RPC response the path is result.content[0].text, parsed, then .json. A chat client unwraps that for you and code talking to the endpoint directly does not.