# Backfill Fetch

> Backfill Fetch is a paid MCP server for web search and scraping. Pay per fetch in USDC to turn web pages into clean markdown or structured JSON. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, Web
- **Website:** https://backfill.top
- **Repository:** https://github.com/maren-ygolonhcet/backfill
- **MCP Registry name:** top.backfill/backfill-fetch
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

Backfill Fetch is aimed at agents that need web content but have no account or API key. Payment happens per call over the x402 protocol in USDC on Base: the server returns the price in a 402 response, the client pays, and the request is resent with the payment header. Payment is verified up front and settled only after content is ready, so failed fetches cost nothing.

A fetch starts with a plain request and escalates to a rendered fetch when the plain one comes back empty, or you choose the mode yourself. Prices listed are free for plain fetches within a daily allowance, $0.005 for a cached page, $0.05 for a fresh rendered fetch and $0.15 for fresh structured extraction. The first 50 fresh plain fetches and 10 cache hits per source address each day are free, and pages are cached for seven days.

Structured extraction takes a URL plus a JSON Schema and returns matching JSON. The site says the product is in development.

## Features

- **Pay per fetch:** No account; x402 payments in USDC on Base.
- **Auto escalation:** Plain fetch first, rendered fetch if empty.
- **Markdown output:** Returns clean page markdown, with raw HTML optional.
- **Structured extraction:** Returns JSON matching a supplied schema.
- **No charge on failure:** Payment settles only after content is ready.
- **Seven-day cache:** Repeat fetches use a cheaper cached price.

## Good for

- Feed an agent readable text from a JavaScript-heavy page
- Extract title and date fields from articles into JSON
- Pay only for successful fetches
- Run web reads from an agent with a crypto wallet

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http backfill-fetch https://backfill.top/mcp
```

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

```sh
https://backfill.top/mcp
```

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

```json
{
  "mcpServers": {
    "backfill-fetch": {
      "url": "https://backfill.top/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "backfill-fetch": {
      "type": "http",
      "url": "https://backfill.top/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "backfill-fetch": {
      "serverUrl": "https://backfill.top/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "backfill-fetch": {
      "type": "http",
      "url": "https://backfill.top/mcp"
    }
  }
}
```

## Tools

- `fetch_page`: Fetch a URL and return clean markdown
- `extract_data`: Extract structured data from a page against a JSON Schema

## FAQ

### What does a fetch cost?

$0.005 cached, $0.05 fresh rendered, $0.15 fresh structured extraction, with a free daily allowance for plain fetches.

### Do I need an account?

No account or API key; payment is via x402.

### Are failed fetches charged?

No.

### How long are pages cached?

Seven days.

### Is Backfill Fetch free?

No. Backfill Fetch is a paid product.

### How do I add Backfill Fetch to Claude Code?

Run this command in your terminal: claude mcp add --transport http backfill-fetch https://backfill.top/mcp

### What are the best alternatives to Backfill Fetch?

The closest alternatives to Backfill Fetch 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/backfill-fetch
