# AIHackr

> AIHackr is a paid MCP server for web search and scraping. Read public webpages as Markdown, extract JSON, list links and run bounded crawls. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://aihackr.com/docs/mcp
- **Repository:** https://github.com/biserd/aihackr-mcp
- **MCP Registry name:** io.github.biserd/aihackr
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

AIHackr's server gives an agent nine web-reading tools over Streamable HTTP. Single-page tools return Markdown, rendered HTML, a page's links, or selected elements, while `get_url_json` extracts structured data with AI inference. For larger jobs, `start_crawl` launches a bounded crawl in your workspace, `get_crawl_result` reads its status and results, and `cancel_crawl` stops it.

The tool list can be read without an account, but every call needs OAuth or an API key. A Markdown scrape costs one credit, listing tools is free, and `get_account` carries no charge. The docs suggest giving the agent a source URL, the fields it needs and a small page bound, then asking it to report failed pages and cite the sources returned.

They also warn that page content is untrusted evidence and should not change the agent's task, a useful reminder for any scraping setup.

## Features

- **Page to Markdown:** Reads a public URL as clean Markdown for one credit.
- **Rendered HTML and links:** Returns rendered HTML or a page's links.
- **Element extraction:** Pulls selected elements from a page.
- **AI JSON extraction:** Turns a page into structured JSON using inference.
- **Bounded crawls:** Start, read and cancel crawls with a page limit.
- **OAuth or API key:** Sign in from a supporting client or use a bearer key.

## Good for

- Summarise a documentation page for an agent
- Collect all links from a landing page
- Extract product fields from several URLs
- Crawl a small site section and report failures
- Test the connection with a fixture page

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http aihackr https://aihackr.com/mcp
```

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

```sh
https://aihackr.com/mcp
```

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

```json
{
  "mcpServers": {
    "aihackr": {
      "url": "https://aihackr.com/mcp"
    }
  }
}
```

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

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

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

```json
{
  "mcpServers": {
    "aihackr": {
      "serverUrl": "https://aihackr.com/mcp"
    }
  }
}
```

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

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

## Tools

- `get_url_html_content`: Get page HTML content Costs 1 credit per successful request.
- `get_url_markdown`: Get page converted into Markdown Costs 1 credit per successful request.
- `scrape_url_elements`: Scrape elements from a page by CSS selector Costs 1 credit per successful request.
- `get_url_json`: Extract structured JSON from a page using AI. Provide a prompt and/or a response_format JSON schema to guide extraction. Costs 5 credits per successful extraction.
- `get_url_links`: Get the list of links on a page Costs 1 credit per successful request.
- `start_crawl`: Start an asynchronous crawl of a website. Returns a job_id — poll get_crawl_result to retrieve records. Workspace maximum: 100 pages and depth 5. Reserves the page limit; charges 1 credit per successful page.
- `get_crawl_result`: Get the status and records of a crawl job started with start_crawl No additional credits; final crawl settlement includes partial successful pages.
- `cancel_crawl`: Cancel a running crawl job No additional credits; final crawl settlement includes partial successful pages.
- `get_account`: Identify the connected AIHackr account.

## FAQ

### Can I see the tools without signing up?

Yes. Clients can list the nine tool schemas without an account, but calling a tool needs OAuth or an API key.

### What does a scrape cost?

A successful Markdown scrape uses one credit; listing tools uses none.

### How do I authenticate?

Use OAuth where the client supports it, or send a bearer API key created in the website's settings.

### Does it handle logged-in pages?

The tools are described for public pages.

### Is AIHackr free?

No. AIHackr is a paid product.

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

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

### What are the best alternatives to AIHackr?

The closest alternatives to AIHackr 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/aihackr
