# Avo Cado Read

> Avo Cado Read is a paid MCP server for web search and scraping. Turn any web page into clean Markdown for agents, paid per call in USDC. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://avocado-read-api.a-347.workers.dev/docs
- **MCP Registry name:** dev.workers.a-347.avocado-read-api/read
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

This service fetches a URL and returns the readable article as Markdown, along with title, byline, site name, language, excerpt, word count, the page's links and a flag for whether the result was truncated or came from cache. There is no account or API key; each call is paid with USDC on Base through the x402 protocol.

Over MCP it exposes `read_url`, which costs $0.003 per call, and a free `pricing` tool. A failed or refused read is not charged. The plain HTTP version has a `/read` endpoint at the same price and a `/ping` connectivity test at $0.001. Calling without payment returns an HTTP 402 with payment instructions.

The service respects robots.txt under the user-agent token AvoCadoReader, does not bypass logins, paywalls or captchas, and refuses private or internal addresses. Fetches time out after 8 seconds, pages are limited to 2 MB and results are cached for an hour.

## Features

- **Clean Markdown output:** Returns readable article text rather than raw HTML.
- **Page metadata:** Includes title, byline, site name, language, excerpt and word count.
- **Link list:** Returns link text and URLs found on the page.
- **x402 payments:** Pay per call in USDC on Base with no account.
- **Polite fetching:** Follows robots.txt and refuses private addresses.
- **Free failures:** Refused or failed fetches are never charged.

## Good for

- Give an agent readable text for a web page without ads or markup
- Extract links from a page for further crawling
- Summarise an article from its Markdown
- Let an autonomous agent pay for page reads without signing up

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http read https://avocado-read-api.a-347.workers.dev/mcp
```

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

```sh
https://avocado-read-api.a-347.workers.dev/mcp
```

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

```json
{
  "mcpServers": {
    "read": {
      "url": "https://avocado-read-api.a-347.workers.dev/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "read": {
      "type": "http",
      "url": "https://avocado-read-api.a-347.workers.dev/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "read": {
      "serverUrl": "https://avocado-read-api.a-347.workers.dev/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "read": {
      "type": "http",
      "url": "https://avocado-read-api.a-347.workers.dev/mcp"
    }
  }
}
```

## Tools

- `read_url`: Fetches a URL and returns clean Markdown; $0.003 per call.
- `pricing`: Free tool that reports pricing.

## FAQ

### How much does a read cost?

$0.003 per call, paid in USDC on Base via x402.

### Do I need an API key?

No. There is no account or key; payment is made per request.

### Are failed fetches charged?

No. 4xx and 5xx responses are never settled.

### What are the limits?

An 8 second fetch timeout, 2 MB page size and a one hour cache.

### Is Avo Cado Read free?

No. Avo Cado Read is a paid product.

### How do I add Avo Cado Read to Claude Code?

Run this command in your terminal: claude mcp add --transport http read https://avocado-read-api.a-347.workers.dev/mcp

### What are the best alternatives to Avo Cado Read?

The closest alternatives to Avo Cado Read are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [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.
- [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.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/avo-cado-read
