# anybrowse

anybrowse uses Chrome to turn web pages into Markdown, search Google, and collect pages from search results. Connect it when an agent needs to read or research web content.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5
- Author: kc23go
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/kc23go/anybrowse
- Updated: 2026-05-26
- HTML: https://affpapa.org/en/nevibecode/mcp/anybrowse

## What it does

This MCP server opens URLs in a real Chrome browser and returns page content as Markdown for an AI agent. It can handle JavaScript-driven sites, dynamic pages, and PDFs. That makes it useful when a task depends on the page itself, not just its URL.

Use `scrape` to fetch a page, `crawl` to search Google and gather pages from the leading results, or `search` to get structured search data. Claude Code connects over HTTP, and setup does not require an API key. Anonymous use is capped at 10 MCP calls per day, so higher-volume use requires a free account or payment.

## Requirements
- Remote server: `https://anybrowse.dev/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http anybrowse https://anybrowse.dev/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add anybrowse --url https://anybrowse.dev/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "anybrowse": {
            "url": "https://anybrowse.dev/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "anybrowse": {
            "type": "http",
            "url": "https://anybrowse.dev/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http anybrowse https://anybrowse.dev/mcp
```

## When to use it
- turn a web page into Markdown for an agent
- gather pages found through Google search
- return search titles, links, and snippets as structured data
- read content from dynamic sites or PDFs

## Example prompts
- Read `https://example.com` and give me the page content as Markdown.
- Search Google for material on this topic and gather the leading pages.
- Search Google and return the result titles, links, and snippets.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32260
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13181
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 13345

---
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