# Hydrafetch

> Hydrafetch is a freemium MCP server for web search and scraping. Remote MCP server that turns any URL into clean Markdown or JSON for agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://hydrafetch.com
- **MCP Registry name:** com.hydrafetch/web
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

Hydrafetch is built around a single response envelope. Each call returns the page content together with a confidence score and flags such as complete and blocked, so a pipeline can retry, review or drop a fetch before it reaches an index. The score is computed from the extraction itself, with no model in the loop.

The API covers scraping a single URL, mapping every URL on a site, crawling a whole site as an asynchronous job with a webhook, running a search whose results arrive already fetched and cleaned, and extracting typed records against a JSON schema. A separate brand endpoint takes a domain and returns logos, ranked colours, fonts and socials, each with its source and confidence.

The MCP server is hosted at api.hydrafetch.com/mcp over streamable HTTP, and the site says every endpoint is exposed as a tool. Official clients exist for six languages, and plain HTTP works too. Billing is per page: one credit for a delivered page, five for model-backed work such as schema extraction and summaries, and failed pages are never charged.

## Features

- **Self-scoring responses:** Every response carries a confidence value and completeness and blocked flags.
- **One response shape:** Scrape, map, crawl, search and extract all return the same envelope.
- **Asynchronous crawls:** Site crawls run as a job with depth, path and subdomain controls and a webhook on completion.
- **Search with fetched results:** Queries return ranked results already fetched and cleaned, with time, region and domain filters.
- **Schema extraction:** Point a JSON schema at a page or site and get typed records with per-field confidence.
- **Brand data:** A domain returns logos for light and dark, ranked colours, fonts and socials.
- **Pay per delivered page:** Errors, blocks and dead ends cost nothing; JS rendering and retries add no extra charge.

## Good for

- Feed an agent clean Markdown from live web pages during a conversation
- Crawl a documentation site into a retrieval index and drop low-confidence pages
- Pull structured records, such as listings, from many pages into a fixed schema
- Fetch a company's logo, colours and fonts to render in an app
- Run a search and get cited, already-cleaned context in one round trip

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http web https://api.hydrafetch.com/mcp
```

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

```sh
https://api.hydrafetch.com/mcp
```

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

```json
{
  "mcpServers": {
    "web": {
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "web": {
      "type": "http",
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "web": {
      "serverUrl": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "web": {
      "type": "http",
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

## FAQ

### How is usage billed?

A successfully delivered page costs one credit. Schema extraction and summaries cost five, search costs one plus one per scraped result, and a styleguide costs ten. Failed pages are never billed.

### Is there a free way to try it?

Signing up with a work email gives 500 free credits on the full API, no card required. They stay valid for 30 days.

### What happens if I exceed my plan?

Usage continues at the plan's overage rate per 10,000 credits instead of stopping mid-job. The Pilot plan lists $11 per 10K in overage.

### Which languages have official clients?

The site lists six: Node, Python, Go, Ruby, Rust and PHP. Plain HTTP with an X-API-Key header also works.

### Does it handle JavaScript-rendered pages and bot walls?

The site says client-side apps come back as content and challenge pages are handled, and that a page which truly cannot be retrieved is reported as such.

### Is Hydrafetch free?

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

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

Run this command in your terminal: claude mcp add --transport http web https://api.hydrafetch.com/mcp

### What are the best alternatives to Hydrafetch?

The closest alternatives to Hydrafetch 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/hydrafetch
