Connect LinkAudit to Claude, Cursor, or your CI pipeline
linkaudit-mcp lets an AI agent scan any site's AI-search visibility, pull a ready-to-paste fix pack, and check real (not estimated) Perplexity citations — without leaving your editor.
Install
Run in your terminal:
claude mcp add linkaudit -- npx -y linkaudit-mcpAdd to claude_desktop_config.json:
{
"mcpServers": {
"linkaudit": {
"command": "npx",
"args": ["-y", "linkaudit-mcp"]
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"linkaudit": {
"command": "npx",
"args": ["-y", "linkaudit-mcp"]
}
}
}Tools
| Tool | What it does |
|---|---|
| run_scan | Full AI-visibility scan: SEO/GEO scores, per-engine ChatGPT/Perplexity/Gemini visibility, top-priority fixes. |
| get_fix_pack | Ready-to-paste files — robots.txt, schema, sitemap, llms.txt, agents.json — built only from real data on the page. |
| check_citability | Is this page "citable" by AI engines? Answer-first structure, quotable passages, question-led headings, FAQ schema. |
| check_perplexity_citations | Measured check: does Perplexity actually cite this domain for real buyer questions — not estimated. |
Lint your GEO score in CI
Same package, no MCP client needed:
npx linkaudit-mcp lint https://your-site.com --min-geo 70 --min-citability 60Exits non-zero (with a readable table of what's failing) if either score is below the threshold — a build step that gates on AI-search visibility the same way you gate on tests.
Environment variables
| Var | Default | Purpose |
|---|---|---|
| LINKAUDIT_API_BASE | https://linkaudit.app | API base URL |
| LINKAUDIT_API_KEY | (none) | Optional bearer token, forwarded as Authorization |
Without an API key, scans share the same free-scan limit as linkaudit.app/scan — it's your own machine's IP making the request.
