# Spicrawl

> Spicrawl is a freemium MCP server for web search and scraping. Scrape any URL to Markdown or JSON, with JavaScript rendering and batch jobs. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, CLI, Web
- **Website:** https://docs.spicrawl.com/agents/mcp
- **Repository:** https://github.com/officialspicrawl/mcp
- **MCP Registry name:** io.github.OfficialSpicrawl/mcp
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

One tool, `spicrawl_scrape`, does most of the work: it reads a URL as Markdown (the default, trimmed to main content), text, HTML, a JSON envelope with heading-split sections, or a printed PDF. The README says Spicrawl picks the cheapest way to satisfy a request. A plain fetch costs 1 credit, JavaScript rendering 3, and screenshots, PDFs or page actions use a full browser at 8; `mode: "auto"` escalates only as far as needed.

Beyond single pages, the server can run batch jobs of up to 10,000 URLs, extract structured data, take screenshots and keep logged-in browser sessions. Usage tools report spend and need a read scope. The browser tools for connect URLs, live view and control need a browser scope that you grant deliberately in the dashboard.

Every call runs under your own API key with its scopes, limits and credits. The hosted endpoint at `https://mcp.spicrawl.com/mcp` takes the key as a bearer token or x-api-key header, never from a URL. Discovery works without a key, but calls return 401. A separate `/chatgpt/mcp` address uses OAuth for ChatGPT. You can also run `npx -y @spicrawl/mcp` locally on Node.js 20 or later. The README says the free tier includes 1,000 credits a month.

## Features

- **Multiple output formats:** Returns Markdown, text, HTML, JSON with sections or a PDF.
- **Tiered rendering:** Plain fetch, JavaScript rendering or full browser, billed by what worked.
- **Batch scraping:** Scrapes up to 10,000 URLs in one job.
- **Browser sessions:** Keeps logged-in sessions and offers live view and control with a scope.
- **Usage reporting:** Reports usage, summaries and reconciliation with a read scope.
- **Key-scoped access:** Calls follow the scopes, limits and credits of your API key.

## Good for

- Read a pricing page into Markdown for an agent
- Scrape a large URL list in one batch
- Capture screenshots or PDFs of pages
- Extract structured data from JavaScript-heavy sites
- Check credit usage from inside an agent

## Install

### Claude Code (Terminal)

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

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

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

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

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

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

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

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

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

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

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

## Tools

- `spicrawl_scrape`: Reads a URL as Markdown, text, HTML, JSON or PDF.
- `spicrawl_usage`: Reports usage; needs read scope.
- `spicrawl_usage_summary`: Summarizes usage; needs read scope.
- `spicrawl_usage_reconciliation`: Reconciles usage; needs read scope.
- `spicrawl_browser_connect_url`: Browser connection URL; needs browser scope.
- `spicrawl_browser_live_view`: Live browser view; needs browser scope.
- `spicrawl_browser_control`: Browser control; needs browser scope.

## FAQ

### What does a scrape cost?

1 credit for a plain fetch, 3 with JavaScript rendering and 8 for screenshots, PDFs or actions.

### Is there a free tier?

The README says the free tier includes 1,000 credits per month.

### How do I authenticate?

Send your Spicrawl API key as a bearer token or x-api-key header; ChatGPT uses a separate OAuth address.

### Can I run it locally?

Yes, with npx -y @spicrawl/mcp on Node.js 20 or later and your API key.

### Is Spicrawl free?

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

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

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

### What are the best alternatives to Spicrawl?

The closest alternatives to Spicrawl 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/spicrawl
