OnPage.dev MCP server

Most SEO tools give you a report. OnPage.dev gives your assistant something to do: write the fix, check it before you publish, and confirm it worked. It also checks what AI search sees, not only Google: which AI crawlers may read your site, whether your content is ready to be quoted, and whether you have an llms.txt.

You:        Fix the SEO on our pricing page and keep going until it scores 90 or more.

Assistant:  scan_page            46/100  no meta description, no H1, title 14 characters
            get_fix_pack         title, description and canonical, written from the page
            generate_schema      Product JSON-LD, 2 values to fill in
            (edits pricing.html)
            scan_html            92/100  before deploying, all errors gone
            rescan_and_compare   94/100  live, +48 since the first scan

            Done. 46 to 94. Two prices in the JSON-LD still need your real values.

Built for agents

What makes OnPage.dev different from every other SEO MCP server:

• Stable issue codes and typed results. Every issue has a fixed code like meta-missing or h1-missing, and the main tools declare an output schema. An agent can work through issues one by one and prove each one is gone.

• It checks the code the agent writes. scan_html, validate_schema and compare_html test new HTML and JSON-LD before it ships, and catch regressions such as a stray noindex or a removed canonical.

• Launch and migration built in. check_urls follows every redirect chain for up to 20 URLs at once; test_robots answers "may this bot fetch this URL" with Google's own matching rules, including * and $ wildcards.

• Whole sites, step by step. start_site_audit runs as a job the agent works through, so a 25-page audit fits a free hosted service. It reports issues across the site by code, broken and orphan pages and duplicates.

• You vs the pages that rank. compare_pages puts a page next to up to 3 competitors with content gaps and fixes to catch up; suggest_internal_links shows which pages should link where.

• No made-up advice. The onpage://rules resource gives the assistant every check, threshold and fix, so it explains SEO from the same rules the scanner uses.

• Free and hosted. Paste one URL. No account, no API key, no install.

Related MCP server: google-seo-mcp

Install in one minute

The server is hosted. There is nothing to install or run, and no key.

Server URL: https://onpage.dev/mcp

claude mcp add --transport http onpage https://onpage.dev/mcp

Or install the plugin for the server plus ready commands and skills.

Settings → Connectors → Add custom connector → paste https://onpage.dev/mcp → save. Turn the connector on in a chat.

Add a custom connector with https://onpage.dev/mcp (Settings → Connectors, with developer mode on). Which plans can use custom connectors is up to OpenAI.

~/.cursor/mcp.json or .cursor/mcp.json in your project:

{
  "mcpServers": {
    "onpage": { "url": "https://onpage.dev/mcp" }
  }
}

.vscode/mcp.json:

{
  "servers": {
    "onpage": { "type": "http", "url": "https://onpage.dev/mcp" }
  }
}

Streamable HTTP transport at https://onpage.dev/mcp. JSON responses, no authentication.

What it can do

20 tools in five jobs. Every result links to the full visual report on onpage.dev. Issues carry stable codes; the full list is in the onpage://rules resource.

Audit and fix

Whole site and competitors

AI search

Launch and migration

Writing and code

Ready workflows (MCP prompts)

One click in clients that show prompts:

• Full SEO and AI audit: scan, AI check and fix pack, then a prioritised plan.

• Why can't AI find my site?: which assistants can read and quote you, and what to change.

• Launch checklist: a tick or cross for everything a page needs before going live.

• AI visibility makeover: robots.txt, llms.txt and answer passages in one go.

• Pre-deploy SEO gate: scan the built HTML and block the release below a minimum score.

Reference resource

onpage://rules: every check with its stable code, why it matters and how to fix it, plus the key thresholds (title and description length in pixels, word counts, alt text, server response, AI answer length).

Score card in the chat

In clients that support MCP Apps (Claude) or the Apps SDK (ChatGPT), scan results also show as a visual card:

Why it is different

What OnPage.dev does not do: search volumes, rankings or backlinks. For those, the data vendors are still the place to go, and they work well alongside OnPage.dev.

Example prompts

Why does ChatGPT never mention example.com? Check it with OnPage.dev.
Scan our pricing page and give me the five fixes with the code.
Let ChatGPT search read our site but block AI training. Write the robots.txt.
We moved to a new URL structure. Check that these 20 old URLs redirect to the right new pages.
Review this pull request for SEO regressions: compare the old and new HTML of the changed pages.
Audit our whole site and tell me the three fixes that help the most pages at once.
We are writing a page about trail running shoes. Which of our pages should link to it?
How does our pricing page compare with these two competitors, and what are we missing?
Does our blog post answer "how long does shipping to Germany take" well enough for AI to quote?
Write three title options for this page and check which ones fit in Google.
Fix the SEO issues in this project, check the build with OnPage.dev and keep going until it scores 95.

Claude Code plugin

The server plus commands and skills that run the fix loop for you.

/plugin marketplace add seoonpage/onpage-tools
/plugin install onpage@onpage-dev

• /seo-check [url or path]: scan a live page, or find this project's built HTML and scan that, then fix what is wrong.

• /ai-visibility: check whether ChatGPT, Claude, Perplexity and Gemini can read and quote the site, and write robots.txt and llms.txt.

• seo-fix-loop skill: fixes in your source (templates, Next.js metadata, Astro frontmatter), checks with scan_html before deploy and confirms with rescan_and_compare after.

About 300 tokens of always-on context.

GitHub Action: SEO gate

Scans the HTML your build produces on every pull request, comments the scores and top fixes, and fails when a page drops below your minimum.

name: SEO gate
on: pull_request
permissions:
  contents: read
  pull-requests: write
jobs:
  seo:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v5
      - run: npm ci && npm run build
      - uses: seoonpage/onpage-tools@v1
        with:
          paths: "dist/**/*.html"          # built HTML to check
          base-url: "https://example.com"   # optional, for canonical and relative links
          min-score: "80"                   # fail below this
          max-files: "10"                   # about 20 scans per minute

The pull request gets a comment like this, updated on every push:

❌ OnPage.dev SEO gate: lowest score 36 (minimum 80)

Page	Score	AI readiness	Fix first
dist/about/index.html	36	0	There is no meta description; There is no H1; The title is 5 characters
dist/index.html	90	22	Thin content: 32 words; No structured data; Open Graph is incomplete

Security and privacy

• Read-only. Every tool only reads public pages or the HTML you send. Nothing is changed anywhere.

• Public pages only. Private, internal and local network addresses are refused (SSRF protection), and so are non-web schemes.

• No storage of content. HTML sent to scan_html is analysed in memory and dropped. For change tracking, only the score and issue names are kept, under a hashed key, for up to 30 days.

• Prompt injection aware. Text from scanned pages is returned as data and marked as such.

• Fair use limits. About 20 scans per minute per connection, plus a shared cap. No accounts, no keys, no tracking cookies.

Full details: onpage.dev/privacy and onpage.dev/terms.

Limits

• Reads the HTML a server returns. JavaScript is not run, so content that only appears in the browser is not seen.

• Link checks, image sizes and AI crawler access need a live URL, so scan_html skips them.

• Pixel widths in check_snippet are an estimate; Google can also rewrite snippets.

Links

• Web app: onpage.dev

• MCP server and setup: onpage.dev/mcp

• Questions: hi@onpage.dev or open an issue

License

MIT