# URLpipe MCP server

> Lets an AI agent render JavaScript-heavy web pages to extract Markdown, screenshots, PDFs, metadata, and Lighthouse audits.

- Repository: https://github.com/URLpipe/mcp
- Page: https://hostedmcp.org/servers/urlpipe/mcp
- Transport: remote
- Stars: 0
- License: MIT
- Latest version: 1.4.0

## Install

### Claude Code

```sh
claude mcp add --transport http mcp https://urlpipe.dev/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://urlpipe.dev/mcp"
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://urlpipe.dev/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp","type":"http","url":"https://urlpipe.dev/mcp"}'
```

### Codex

```sh
codex mcp add mcp --url https://urlpipe.dev/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp]
url = "https://urlpipe.dev/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http mcp https://urlpipe.dev/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://urlpipe.dev/mcp",
      "type": "http"
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `URLPIPE_AUTH` | no | no |  |

## Tools (17)

- `list_projects`
- `get_usage`
- `fetch_markdown`
- `fetch_html`
- `capture_screenshot`
- `capture_pdf`
- `capture_console_errors`
- `run_lighthouse_audit`
- `extract_metadata`
- `detect_technologies`
- `extract_keywords`
- `summarize_page`
- `extract_data`
- `scrape_url`
- `get_result`
- `list_requests`
- `get_request`

## FAQ

### How does URLpipe handle JavaScript-heavy sites like React or Vue?

URLpipe loads every page in a real Chrome browser first, ensuring the agent receives the fully rendered content rather than an empty shell.

### Can I use URLpipe for free?

Yes, you get 1,000 free credits every month without needing a credit card, and cached results cost nothing.

### Does URLpipe crawl entire websites?

No, it is designed to answer questions about one URL at a time and does not crawl whole sites or discover new URLs.

### Where is the data processed?

All fetching, rendering, and storage operations are processed within the EU.
