# scrapeless-mcp-server

Gives your agent web access: Google search, trends, browser automation, scraping and CAPTCHA solving.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 170
- Author: scrapeless-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/scrapeless-ai/scrapeless-mcp-server
- Updated: 2026-09-08
- HTML: https://affpapa.org/en/nevibecode/mcp/scrapeless-mcp-server

## What it does

The server follows the open MCP standard and wires a model into external web capabilities. It covers Google search, Google Trends data, browser automation for navigation and clicks, scraping of dynamic pages with output as HTML, Markdown or a screenshot, crawling sites by following links, and CAPTCHA solving. A separate tool creates AI Scraper tasks.

Two transports are available: local Stdio via `npx`, or the hosted endpoint at `https://api.scrapeless.com/mcp` over Streamable HTTP. Both need a Scrapeless key, created in the dashboard and passed as `SCRAPELESS_API_KEY` or in the `x-api-token` header. No key, no server.

Browser session behaviour is tunable with optional parameters: `BROWSER_PROFILE_ID` for a reusable profile, `BROWSER_PROFILE_PERSIST` to keep cookies and local storage, `BROWSER_SESSION_TTL` for the maximum session timeout in seconds. In Stdio these are environment variables; over HTTP they become headers with an `x-` prefix.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://api.scrapeless.com/mcp`
- Environment variables: `SCRAPELESS_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 scrapeless-mcp-server -e SCRAPELESS_API_KEY=<SCRAPELESS_API_KEY> -- npx -y scrapeless-mcp-server
```
Replace <…> with your own values

2. **Platform CLI: remote server**
```bash
claude mcp add --transport http scrapeless-mcp-server https://api.scrapeless.com/mcp
```

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add scrapeless-mcp-server --url https://api.scrapeless.com/mcp
```

2. **Platform CLI**
```bash
codex mcp add scrapeless-mcp-server --env SCRAPELESS_API_KEY=<SCRAPELESS_API_KEY> -- npx -y scrapeless-mcp-server
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapeless-mcp-server": {
            "url": "https://api.scrapeless.com/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "scrapeless-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "scrapeless-mcp-server"
            ],
            "env": {
                "SCRAPELESS_API_KEY": "<SCRAPELESS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapeless-mcp-server": {
            "type": "http",
            "url": "https://api.scrapeless.com/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "scrapeless-mcp-server": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "scrapeless-mcp-server"
            ],
            "env": {
                "SCRAPELESS_API_KEY": "<SCRAPELESS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http scrapeless-mcp-server https://api.scrapeless.com/mcp
```

2. **Platform CLI**
```bash
gemini mcp add -e SCRAPELESS_API_KEY=<SCRAPELESS_API_KEY> scrapeless-mcp-server npx -y scrapeless-mcp-server
```
Replace <…> with your own values

## When to use it
- pull content from a page that renders through JavaScript
- get past Cloudflare and read the target page
- collect Google results for a keyword with titles and links
- follow a site's links and save every page as Markdown
- take a page screenshot straight from the chat

## Example prompts
- Search Google for "web scraping", grab the first 10 results and write them to `serp.text`
- Open `chatgpt.com` in a browser, ask about today's weather and summarize the answer
- Scrape the Markdown of `scrapeless.com` and save it to `text.md`

## Similar
- [browser-act](https://affpapa.org/en/nevibecode/skills/browser-act.md) — skill · 108300 installs
- [steel-reliability](https://affpapa.org/en/nevibecode/skills/steel-reliability.md) — skill · 432 installs
- [FrankenSurf](https://affpapa.org/en/nevibecode/mcp/frankensurf.md) — MCP server · ★ 102
- [scraping-google-search-results](https://affpapa.org/en/nevibecode/skills/scraping-google-search-results.md) — skill · 759 installs
- [EveryInfra](https://affpapa.org/en/nevibecode/mcp/everyinfra.md) — MCP server · ★ 80
- [google-search-browser-use](https://affpapa.org/en/nevibecode/skills/google-search-browser-use.md) — skill · 1900 installs

---
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