# Crawlinx

Crawlinx — a hosted MCP server for automated technical SEO audits. It runs 156 checks, generates compact reports for AI agents, and compares scans after fixes.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 372 installs
- Author: antropov-akim71
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/antropov-akim71/crawlinx
- Updated: 2026-07-11
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/crawlinx

## What it does

Crawlinx runs as a remote service over Streamable HTTP without local binaries, account registration, or access tokens. An agent calls `scan_url` to inspect a domain, crawling 50 pages by default or up to 200 when setting `max_pages`. The engine inspects 156 technical points, covering title tags, canonical links, noindex flags, orphan URLs, internal PageRank, JS rendering differences, asset sizing, and sitemaps.

Output comes as structured JSON via `get_report` or as a concise table through `get_report_markdown`, designed to preserve prompt context. When an agent tackles a specific error code, `get_issue_detail` returns every affected URL alongside remediation advice.

After applying changes, the agent calls `diff_scan` to verify resolved errors and flag any regressions against the previous crawl. Because processing happens on the hosted endpoint, the host machine requires only outbound internet connectivity.

## Requirements
- Remote server: `https://crawlinx.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http crawlinx https://crawlinx.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add crawlinx --url https://crawlinx.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "crawlinx": {
            "url": "https://crawlinx.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "crawlinx": {
            "type": "http",
            "url": "https://crawlinx.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http crawlinx https://crawlinx.run.tools
```

## When to use it
- detect broken canonical tags and orphan URLs across crawled pages
- spot layout or content discrepancies caused by client JavaScript rendering
- pull step-by-step remediation instructions for technical SEO defects
- compare sequential domain crawls to confirm fixes and catch regressions

## Example prompts
- Start a technical SEO crawl on the target site with `scan_url`.
- Fetch the summary using `get_report_markdown` and prioritize high-severity items.
- Run `diff_scan` against the prior scan to confirm our changes worked.

## Similar
- [Black SEO Analyzer](https://affpapa.org/en/nevibecode/mcp/black-seo-analyzer.md) — MCP server · ★ 61 repo stars
- [中文 AI 可引用性（GEO/AEO）体检](https://affpapa.org/en/nevibecode/mcp/ai-geoaeo.md) — MCP server · ★ 1 repo stars
- [audit-website](https://affpapa.org/en/nevibecode/skills/audit-website.md) — skill · 75200 installs
- [firecrawl-seo-audit](https://affpapa.org/en/nevibecode/skills/firecrawl-seo-audit.md) — skill · 32400 installs
- [seo-audit](https://affpapa.org/en/nevibecode/skills/agricidaniel-seo-audit.md) — skill · 9200 installs
- [revnu-ai-crawler-access](https://affpapa.org/en/nevibecode/skills/revnu-ai-crawler-access.md) — skill · 3400 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
