# HasData Google Search (SERP)

Eight Google Search tools over MCP: organic, AI Overview, People Also Ask, AI Mode, news, shopping — all as JSON. No Google Cloud setup.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 16
- Author: HasData
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/HasData/google-search-mcp
- Updated: 2026-10-12
- HTML: https://affpapa.org/en/nevibecode/mcp/hasdata-google-search-serp

## What it does

Returns Google search results as structured JSON. The response includes organic listings, AI Overview and People Also Ask blocks, news, product cards, and short videos. You can run an AI Mode query to get a generated answer with citations. A separate call expands product details: stores, price range, and review breakdown.

Remote server running over streamable HTTP. Requires a HasData API key from the dashboard — free sign-up with no card gives 1,000 credits monthly (100–200 calls depending on the tool). Stdio-only clients can use the `@hasdata/google-search-mcp` npm package or `hasdata-google-search-mcp` PyPI package as a launcher.

Eight tools total. A full SERP costs 10 credits, expanding a product card costs 5. No Programmable Search Engine or cloud project needed.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://mcp.hasdata.com/mcp?apis=google_serp`
- Environment variables: `HASDATA_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI**
```bash
claude mcp add google-search -e HASDATA_API_KEY=<HASDATA_API_KEY> -- npx -y @hasdata/google-search-mcp
```
Replace <…> with your own values

2. **Platform CLI: remote server**
```bash
claude mcp add --transport http hasdata-google-search-serp 'https://mcp.hasdata.com/mcp?apis=google_serp'
```

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add hasdata-google-search-serp --url 'https://mcp.hasdata.com/mcp?apis=google_serp'
```

2. **Platform CLI**
```bash
codex mcp add hasdata-google-search-serp --env HASDATA_API_KEY=<HASDATA_API_KEY> -- npx -y @hasdata/google-search-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "hasdata-google-search-serp": {
            "url": "https://mcp.hasdata.com/mcp?apis=google_serp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "hasdata-google-search-serp": {
            "command": "npx",
            "args": [
                "-y",
                "@hasdata/google-search-mcp"
            ],
            "env": {
                "HASDATA_API_KEY": "<HASDATA_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "hasdata-google-search-serp": {
            "type": "http",
            "url": "https://mcp.hasdata.com/mcp?apis=google_serp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "hasdata-google-search-serp": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@hasdata/google-search-mcp"
            ],
            "env": {
                "HASDATA_API_KEY": "<HASDATA_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http hasdata-google-search-serp 'https://mcp.hasdata.com/mcp?apis=google_serp'
```

2. **Platform CLI**
```bash
gemini mcp add -e HASDATA_API_KEY=<HASDATA_API_KEY> hasdata-google-search-serp npx -y @hasdata/google-search-mcp
```
Replace <…> with your own values

## When to use it
- fetch AI Overview alongside organic results
- extract People Also Ask questions with sources
- run AI Mode and retrieve the answer with citations
- search Google Shopping and expand product cards
- pull news or short-video results for a query

## Example prompts
- For each People Also Ask question, pull its AI Overview answer with sources
- Ask Google AI Mode `what is the Model Context Protocol` and show me the answer with citations

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md