# zlurp

zlurp extracts public web pages into formatted markdown for agents, handling payments via Base network micropayments.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 2458 installs
- Author: zlurp
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/zlurp/zlurp
- Updated: 2026-05-13
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/zlurp

## What it does

The server equips AI assistants with tools to ingest remote web pages directly into context. It separates estimation from execution: `probe_url` calculates scraping fees beforehand at no cost.

The actual extraction runs through `scrape_url`, which formats HTML into markdown. Each successful call costs 0.005 USDC charged through x402 protocol on Base, so the connected environment needs a configured micropayment channel.

## Requirements
- Remote server: `https://zlurp--zlurp.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http zlurp https://zlurp--zlurp.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add zlurp --url https://zlurp--zlurp.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "zlurp": {
            "url": "https://zlurp--zlurp.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "zlurp": {
            "type": "http",
            "url": "https://zlurp--zlurp.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http zlurp https://zlurp--zlurp.run.tools
```

## When to use it
- Check url scraping expenses before running queries
- Fetch remote articles as structured markdown
- Pay for single page fetches via USDC micropayments

## Example prompts
- Estimate the cost to scrape the target page with probe_url
- Extract the content of the documentation page into markdown using scrape_url

## Similar
- [xenarch-mcp](https://affpapa.org/en/nevibecode/mcp/xenarch-mcp.md) — MCP server · 974 installs
- [mcp-x402](https://affpapa.org/en/nevibecode/mcp/mcp-x402.md) — MCP server · ★ 279 repo stars
- [Neuronto Payments: x402 facilitator and API gateway](https://affpapa.org/en/nevibecode/mcp/neuronto-payments-x402-facilitator-and-api-gateway.md) — MCP server
- [competitor-profiling](https://affpapa.org/en/nevibecode/skills/competitor-profiling.md) — skill · 107300 installs
- [firecrawl](https://affpapa.org/en/nevibecode/skills/firecrawl.md) — skill · 104500 installs
- [defuddle](https://affpapa.org/en/nevibecode/skills/defuddle.md) — skill · 76500 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
