AutoRank MCP
Technical SEO tools for AI agents. Generate and validate structured data, build
meta tags and crawl directives, check how a result will actually render in
Google, and analyse copy — all from inside Claude, Cursor, or any MCP client.
No API key. No account. No network calls. Every tool is a pure function, so
the server does its job offline and installs in one line.
Browser versions of these tools live at
autorank.so/free-tools.
Install
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"autorank": {
"command": "uvx",
"args": ["autorank-mcp"]
}
}
}
Or with pip:
Then point your client at the autorank-mcp command. No environment variables
are required.
Structured data
| Tool | What it does |
|---|
generate_faq_schema | FAQPage JSON-LD from question/answer pairs |
generate_article_schema | Article JSON-LD with author and dates |
generate_breadcrumb_schema | BreadcrumbList JSON-LD |
generate_local_business_schema | LocalBusiness JSON-LD with postal address |
validate_json_ld | Parses a block, checks required fields per type, flags risky patterns |
| Tool | What it does |
|---|
generate_meta_tags | Full head block: title, description, canonical, OG, Twitter Card |
generate_robots_meta | Robots meta tag from directives, with a plain-English explanation |
generate_robots_txt | robots.txt, optionally blocking the major AI crawlers |
validate_robots_txt | Validates syntax and surfaces the mistakes that cause real damage |
generate_hreflang | hreflang tags, with the return-link requirement spelled out |
SERP and copy
| Tool | What it does |
|---|
check_title_length | Pixel-width truncation check for titles |
check_description_length | Pixel-width truncation check for descriptions |
serp_preview | How the whole result renders, breadcrumb included |
keyword_density | Word and phrase frequency with a stuffing warning |
readability_score | Flesch Reading Ease and grade level |
Utilities
| Tool | What it does |
|---|
build_utm_link | UTM-tagged tracking URLs, warns on case-inconsistency |
slugify | Clean URL slugs from titles |
autorank_free_tools | Lists the web-only tools that need live crawling |
Design notes
Title checks measure pixels, not characters. Google truncates on rendered
width, and character counts mislead badly — sixty capital Ws and sixty is
occupy very different space. Titles are the most common cause of a rewritten
snippet, so the check approximates width instead.
The schema tools will not help you lie. validate_json_ld flags
aggregateRating whenever it appears, because fabricated ratings are a
documented cause of manual actions, and generate_faq_schema states plainly
that the answers must already be visible on the page. Structured data that
disagrees with rendered content is a spam signal, not a shortcut.
Some tools are deliberately absent. Anything needing live crawling or a
keyword corpus — broken-link checking, keyword difficulty, sitemap extraction,
duplicate-content detection — is not a pure function, so it stays on the web
where it belongs. autorank_free_tools lists those.
robots.txt controls crawling, not indexing. validate_robots_txt says so in
its output, because conflating the two is the single most common way sites
accidentally leave pages in the index.
Development
git clone https://github.com/RyanKramer/autorank-mcp
cd autorank-mcp
pip install -e .
autorank-mcp
About
Built by AutoRank — AI SEO content automation. The web
versions of these tools, plus about thirty more, are free at
autorank.so/free-tools.
MIT licensed.