{
  "markdown": "# Crawlinx MCP\n\n> Free technical-SEO audit as an MCP server — built for AI coding agents.\n\n[![smithery badge](https://smithery.ai/badge/antropov-akim71/crawlinx)](https://smithery.ai/servers/antropov-akim71/crawlinx)\n\n**Crawlinx** is a hosted [Model Context Protocol](https://modelcontextprotocol.io) server that lets your AI agent audit a website's technical SEO and act on the results. It crawls a site (50 pages by default, up to 200 via `max_pages`), runs 156 technical-SEO checks, and returns an **LLM-ready Markdown report with a prioritized fix plan** — small enough to keep in context on a real site.\n\n- ☁️ **Remote server over Streamable HTTP** — no local install, no API key, no signup\n- 🔎 **156 checks** — titles, meta, canonicals, orphan pages, noindex, internal PageRank, JS render-diff, images, performance, sitemap\n- 🤖 **Agent-native** — compact reports, per-issue drill-down, and scan diffs so an agent can **scan → fix → verify** in a loop\n- 🔗 **Public shareable reports** — every scan has a URL\n\nHomepage: **https://crawlinx.com** · Docs: **https://crawlinx.com/api**\n\n## Install\n\nThe server is remote — you only need the endpoint `https://crawlinx.com/mcp`. No key.\n\n### Claude Code\n```bash\nclaude mcp add --transport http crawlinx https://crawlinx.com/mcp\n```\n\n### Cursor / Windsurf / Cline / Claude Desktop\nAdd to your MCP config (`mcp.json` / settings):\n```json\n{\n  \"mcpServers\": {\n    \"crawlinx\": {\n      \"type\": \"http\",\n      \"url\": \"https://crawlinx.com/mcp\"\n    }\n  }\n}\n```\n\nA machine-readable manifest is served at [`/.well-known/mcp.json`](https://crawlinx.com/.well-known/mcp.json).\n\n## Tools\n\n| Tool | What it does |\n|------|--------------|\n| `scan_url` | Start a free SEO audit of a URL (crawls `max_pages` pages — default 50, max 200); returns a scan id. |\n| `get_report` | Fetch a finished report as structured JSON. |\n| `get_report_markdown` | Fetch a finished report as compact, LLM-ready Markdown (health score + prioritized fix plan + issues collapsed by code). Set `full=true` for the complete report. |\n| `get_issue_detail` | Expand one issue code: every affected URL plus step-by-step remediation. |\n| `diff_scan` | Diff a scan against the previous scan of the same domain to confirm fixes landed and nothing regressed. |\n\n## Example prompts\n\n- *\"Audit https://example.com and give me the top 5 SEO fixes.\"*\n- *\"Scan my site, then fix the duplicate `<title>` issues in the codebase and re-scan to confirm.\"*\n- *\"Which pages are orphaned (no internal links) and how do I link them?\"*\n\n## Typical workflow\n\n1. `scan_url` → get a `scan_id`\n2. poll `get_report_markdown` until the crawl finishes\n3. `get_issue_detail(scan_id, code)` to expand a specific issue before changing code\n4. apply fixes\n5. re-scan, then `diff_scan(scan_id)` to verify\n\n## The crawler\n\nAudits run as `CrawlinxBot`, which honors `robots.txt`, limits request rates, and does not bypass access controls. See [crawlinx.com/bot](https://crawlinx.com/bot). Site owners can opt out via robots.txt or the removal form.\n\n## Maintenance & rankings\n\nThis MCP is a **living product** — aggregators (Smithery Quality Score, polygraph.so security grades, MCP Bench) actively **rank and grade** it, and the Official Registry cascades our listing everywhere. Keep the endpoint healthy and re-publish on changes. See **[MAINTENANCE.md](MAINTENANCE.md)**.\n\n## About\n\nThis repository documents the hosted Crawlinx MCP server. The audit engine is operated as a service at [crawlinx.com](https://crawlinx.com); this repo is the public reference and install guide for the MCP integration.\n",
  "bytes": 3581,
  "sha": "e4454d3221eb811fab2f3e9f1268ecdbceea6c71299b1fa925a0fde9083f8633",
  "repo_slug": "im-ff/crawlinx-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_im_ff_crawlinx_mcp_abe17a55/readme"
}