# google-surf-mcp-search

google-surf-mcp-search — a skill configuring Google search without API keys alongside PDF extraction for academic papers. It strips search ads and handles CAPTCHAs via browser profiles.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 212 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/google-surf-mcp-search/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/google-surf-mcp-search

## What it does

This skill integrates an MCP engine that queries Google directly through a real browser session. It strips sponsored links and search widgets using geometric layout checks. Results stay clean. You can also run batch queries across a worker pool supporting up to 10 queries simultaneously.

Web page scraping handles standard HTML alongside research PDFs from sources like arXiv, Nature, or PubMed. A dedicated triage mode limits output to roughly 1500 characters. That saves tokens. Full text mode remains available when complete document text is needed.

Execution depends on a local Chrome installation. The path is set through the `CHROME_PATH` variable. Persistent browser sessions live under `~/.google-surf-mcp`, preventing recurring bot verification blocks.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill google-surf-mcp-search -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/google-surf-mcp-search/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/google-surf-mcp-search/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill google-surf-mcp-search -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/google-surf-mcp-search/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill google-surf-mcp-search -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/google-surf-mcp-search/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/google-surf-mcp-search
```

2. **Manually: put the files in place**
- File: `.github/skills/google-surf-mcp-search/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill google-surf-mcp-search -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/google-surf-mcp-search
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/google-surf-mcp-search/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill google-surf-mcp-search -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/google-surf-mcp-search/SKILL.md

## When to use it
- query Google search without managing paid API tokens
- pull text directly from online academic PDFs and arXiv papers
- strip sponsored ads and widget panels from search responses
- run up to 10 search queries in parallel within one step

## Example prompts
- Search Google for recent papers on context window optimization and extract 1500-character abstracts
- Fetch the full article text from https://arxiv.org/pdf/2301.12345.pdf
- Run a parallel search for three different TypeScript caching strategies

## Similar
- [google-search-browser-use](https://affpapa.org/en/nevibecode/skills/google-search-browser-use.md) — skill · 1900 installs
- [scraping-google-search-results](https://affpapa.org/en/nevibecode/skills/scraping-google-search-results.md) — skill · 917 installs
- [finding-law-firms-via-google-search](https://affpapa.org/en/nevibecode/skills/finding-law-firms-via-google-search.md) — skill · 919 installs
- [linkfox-ai-mode-google-search](https://affpapa.org/en/nevibecode/skills/linkfox-ai-mode-google-search.md) — skill · 232 installs
- [google-search](https://affpapa.org/en/nevibecode/skills/google-search.md) — skill · 4800 installs
- [google-search-agent-teneo](https://affpapa.org/en/nevibecode/skills/google-search-agent-teneo.md) — skill · 521 installs

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
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
