Skip to main content

SEO that
runs itself.

Runs on your own Claude key. No AI markup, ever. $99/mo only when you want the agent to run itself.

claude code

$ npx seolint-mcpNo AI markup. Your Claude key, encrypted at rest.

How it works

The loop you stop thinking about.

The agent watches, Search Console data grades every fix, Claude ships them.

Step 1

The agent watches

Weekly auto-scans find what changed since your last deploy. New issues, regressions, and opportunities caught without you asking.

Step 2

Search Console grades the fix

Your Search Console metrics sync daily per URL. After a fix ships, the agent tracks clicks, impressions, and position against the baseline. No generic severity scores, real traffic decides whether it worked.

Step 3

Claude ships the fix

Connect via MCP. Claude Code, Cursor, or Windsurf reads the issue and writes the fix in your codebase. You approve, it commits.

CriticalPerformance

Slow Largest Contentful Paint (4.0s)

LCP is exactly at Google's “poor” threshold of 4s. One more ms and Core Web Vitals fail.

Why this matters here

Your hero image is the LCP element, and blocking scripts in <head> delay it by ~1s. Compressing and prioritizing the hero is the fastest ranking win.

Fix prompt

In app/layout.tsx, add fetchPriority="high" to the hero <img>, serve it as WebP under 80KB, and add defer to non-critical scripts.

Step 1 · Scanner

The agent watches your site.

Every issue comes back as broken HTML plus an AI-ready fix prompt. Run scans weekly on autopilot, or on demand from MCP, CLI, or dashboard.

  • Broken element extracted from your page, not a generic warning
  • Fix prompt designed for Claude Code, Cursor, or any AI agent
  • 40+ checks across SEO, performance, accessibility, and AEO
Try a scan

Step 2 · Memory

Memory remembers every scan.

The agent carries full context to every conversation. Ask Claude what is broken or what to build next, it already knows the site history.

  • Issues labeled NEW, PERSISTING, REGRESSED across scans
  • Site profile: goal, audience, niche inferred on first scan
  • Visual review: screenshot scored against your ICP
  • Content gaps: missing pages suggested from your sitemap
Screenshot of seolint.dev

seolint.dev

7 scans · 42 days tracked · 50 URLs in sitemap

↑ Improving
B2B SaaSDeveloper toolsSEO
Feb 22Today
NEW

Slow LCP (4.0s) on homepage

2h ago
FIXED

Missing og:image on /pricing

3d ago
REGRESSED

H1 missing on /blog

5d ago

Content gaps · 3 page ideas

Getting started with SEOLint

/docs/quickstart

info

SEOLint vs Ahrefs: SEO for AI agents

/vs/ahrefs

commercial

Insight: Strong blog coverage but no comparison pages vs direct competitors. One-hour content win.

Is my site improving? Fix anything critical.

● get_site_status (MCP)

Improving · 6 scans · 32d tracked

● scan_website (MCP)

1 new · 1 persisting

● Edit(app/layout.tsx)

- <title>Home</title>

+ <title>Best CRM for small teams</title>

1 critical issue fixed. Memory updated.

Step 3 · MCP

Fix it inside Claude.

Connect SEOLint as an MCP server. Claude Code, Cursor, or any AI agent reads the issue and writes the fix in your codebase. You approve, it commits.

  • Works in Claude Code, Cursor, Windsurf, Claude Desktop, and custom agents
  • 8 tools: scan, history, site intelligence, page suggestions, resolve, and more
  • GitHub Actions: fail builds when fixed issues regress

Step 4 · PR agent

Coming soon

And the agent writes the PR too.

Connect a GitHub repo and the agent opens a pull request with the fix, waits for your CI to go green, then hands it to you for review. Mechanical fixes first: meta, alt, canonical, schema, sitemap.

acmeshop/site · #142

Openseolint-bot wants to merge 1 commit

fix(seo): add meta descriptions to 3 product pages

Flagged in last 3 scans. Drafted descriptions based on page content and your existing voice. Each is 140–155 chars.

+ app/products/trail-shoes/page.tsx

+ app/products/waterproof/page.tsx

+ app/products/lightweight/page.tsx

3 files changed · 12 additionsChecks passing

How we work

A dev tool first. An agent when you want one.

Free gives you the full linter: scanner, memory, Search Console grading, MCP. Upgrade when you want it running itself.

Free · dev tool

$0/mo

The full linter on your own Claude API key. No card.

  • Scan with your own Claude API key
  • First scan is on us, no key needed yet
  • Every check (40+) with AI fix prompts
  • Full memory: history, site profile, insights
  • Google Search Console + per-fix grading
  • Dashboard, CLI, and MCP (read tools)
  • 100 scans per day
Start scanning

For developers who want SEO to behave like a linter.

Autonomous agent

$99/mo

Everything in Free plus the coworker that runs itself.

  • Weekly auto-scans. The agent watches, you don't.
  • 1 site under agent watch, up to 200 pages tracked
  • AI next-action oracle: what to fix next
  • MCP write tools (mark-fixed, dismiss)
  • GitHub PR bot ships fixes as pull requests (soon)
  • Interactive email agent (soon)
  • Still runs on your Claude API key. We cover the infra.
  • 7-day free trial. 1,000 scans / mo on any site.
Start 7-day free trial

For founders who want SEO handled, not tooled.

Running multiple sites or an agency? Custom plans →

Stop thinking about SEO.

Sign up in 30 seconds. No credit card. Bring your Claude key.

Start free

Listed on

Listed on SaaSCityListed on Wired BusinessListed on Twelve ToolsListed on LaunchIgniterSEOLint - Listed on Startup Fame