# URLpipe

> URLpipe is a freemium MCP server for web search and scraping. Give agents a real Chrome that renders JavaScript: Markdown, screenshots, Lighthouse. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://urlpipe.dev/mcp-server
- **Repository:** https://github.com/urlpipe/mcp
- **MCP Registry name:** dev.urlpipe/mcp
- **Categories:** web search and scraping, browser automation
- **Listing updated:** 2026-11-15

## About

Plain fetch tools return an empty shell on React, Vue or Angular pages, and the agent may not realise it read nothing. URLpipe loads each page in real Chrome first, and its hosted server then hands back whichever view is requested: rendered Markdown or HTML, a screenshot the agent can inspect, a PDF, metadata, console errors, detected technologies or a Lighthouse audit.

There are 17 tools. Twelve map to the HTTP API with the same arguments, and five exist only in MCP, including result history, projects and usage. Calls return a token at once and finish in the background unless you pass sync: true. Tokens are separate from project API keys and can be read-only, limited to a project or set to expire. Fetching, rendering and storage run in the EU.

Costs are in credits: fetch_markdown is 1, summarize_page is 17, and cache hits are free. The author's own comparison recommends the reference fetch server for static pages when you want everything local and free.

## Features

- **Rendered Markdown:** fetch_markdown converts the browser-rendered DOM to clean Markdown for 1 credit.
- **Screenshots and PDF:** Capture a page the agent can view, or print it to PDF.
- **Console and Lighthouse:** Read JavaScript console output or run a full Lighthouse audit.
- **Metadata and tech stack:** Title, description, dates, feeds and detected CMS or frameworks.
- **AI endpoints:** summarize_page, keywords and schema-based extraction cost more credits.
- **Scoped tokens:** Bearer tokens can be read-only, per project or expiring.

## Good for

- Read a single-page app that a plain fetch returns blank
- Screenshot a staging page to check a layout change
- Collect console errors from a deployed site
- Pull structured data from a page into your own schema

## Install

### Claude Code (Terminal)

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

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
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"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## Tools

- `fetch_markdown`: Rendered page as Markdown, 1 credit
- `summarize_page`: Written summary of a page, 17 credits

## FAQ

### Does it need OAuth?

No. Add a bearer token header; there is no OAuth flow and nothing runs locally.

### What does the free plan include?

1,000 credits a month with no card, one request at a time.

### Do cached results cost credits?

No, cache hits are free and the default max_age is 7 days.

### What happens on failed fetches?

Failed targets, robots.txt-blocked pages and unbypassed bot checks spend no credits.

### Where is data processed?

The README says fetching, rendering and storage happen in Europe.

### Is URLpipe free?

URLpipe has a free plan, with paid plans for more usage or features.

### How do I add URLpipe to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://urlpipe.dev/mcp

### What are the best alternatives to URLpipe?

The closest alternatives to URLpipe are Browser Use, Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search and Oya Browser.

## Alternatives

- [Browser Use](https://ai-powered.com/mcp/browser-use): Browser Use is a freemium MCP server for browser automation.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [Mantis](https://ai-powered.com/mcp/mantis-2): Mantis is an open-source MCP server for browser automation.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/urlpipe
