# scrape-agent-mcp

Scrapes clean text, links, or HTML markup on demand using x402 micropayments. Charges 0.01 USDC on Base per request without API keys or ongoing plans.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 109 installs · ★ 1 repo stars
- Author: artespraticas
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/artespraticas/scrape-agent-mcp
- Updated: 2026-06-04
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/scrape-agent-mcp

## What it does

The server exposes an operation named `scrape_url`. It inspects public web resources and extracts sanitized text, outbound hyperlinks, or raw HTML markup. This design helps autonomous agents retrieve online context without running dedicated browser infrastructure.

Instead of personal access tokens, requests rely on x402 micropayments. Every extraction costs 0.01 USDC on the Base network. Incoming GET or POST traffic missing an `X-PAYMENT` header triggers an HTTP 402 code with an `accepts[]` response. The OpenAPI contract is served at `/openapi.json`.

## Requirements
- Remote server: `https://scrape-agent-mcp--artespraticas.run.tools`

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- extract sanitized body text from a webpage at `<url>`
- collect outbound hyperlinks from an online resource
- pull raw HTML markup without registering an account
- pay strictly per page fetch using 0.01 USDC on Base

## Example prompts
- Run `scrape_url` on `<url>` and return clean text
- Extract all outbound links from `<url>`
- Fetch the raw HTML content of `<url>`

## Similar
- [x402](https://affpapa.org/en/nevibecode/skills/x402.md) — skill · 1500 installs
- [Popdot AI](https://affpapa.org/en/nevibecode/mcp/popdot-ai.md) — MCP server
- [WebberSites x402 Data API](https://affpapa.org/en/nevibecode/mcp/webbersites-x402-data-api.md) — MCP server · 832 installs
- [x402farm](https://affpapa.org/en/nevibecode/mcp/x402farm.md) — MCP server · 137 installs
- [AgentNDX](https://affpapa.org/en/nevibecode/mcp/agentndx.md) — MCP server · 4376 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
