Skip to main content
Glama
Sign In
AutoRank MCP

AutoRank MCP

by RyanKramer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

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:

pip install autorank-mcp

Then point your client at the autorank-mcp command. No environment variables are required.

Related MCP server: SEO Screaming Toad MCP Server

Tools

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

Meta and crawl directives

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.

Available Tools

18 tools
autorank_free_toolsC

List the browser versions of these tools, plus the ones not exposed here.

Inputs: no named parameters. Returns: object

build_utm_linkB

Build a UTM-tagged tracking URL.

Inputs: url (required), medium (required), source (required), campaign (required), +2 more. Returns: object

check_description_lengthB

Check whether a meta description will be truncated in Google results.

Inputs: description (required). Returns: object

check_title_lengthA

Check whether a page title will be truncated in Google results.

Measures approximate pixel width rather than character count, because Google truncates on width. Returns the estimate, the limit, and a verdict.

Inputs: title (required). Returns: object

generate_article_schemaC

Generate Article JSON-LD. Dates should be ISO 8601 (YYYY-MM-DD).

Inputs: headline (required), author_name (required), date_published (required), image_url, +3 more. Returns: result

generate_breadcrumb_schemaA

Generate BreadcrumbList JSON-LD. Each item needs 'name' and 'url'.

Inputs: items (required). Returns: result

generate_faq_schemaA

Generate FAQPage JSON-LD. Each item needs 'question' and 'answer'.

The answers MUST already be visible on the page. Schema that disagrees with the rendered page is a spam signal, not a shortcut.

Inputs: questions_and_answers (required). Returns: result

generate_hreflangA

Generate hreflang link tags. Each page needs 'lang' (e.g. en-us) and 'url'.

Every listed page must carry the full set, including a self-reference, or the cluster is ignored.

Inputs: pages (required), include_x_default. Returns: result

generate_local_business_schemaC

Generate LocalBusiness JSON-LD with a postal address.

Inputs: city (required), name (required), region (required), country (required), +5 more. Returns: result

generate_meta_tagsA

Generate a complete head block: title, description, canonical, Open Graph and Twitter Card tags. Returns HTML ready to paste.

Inputs: title (required), description (required), canonical_url (required), image_url, +2 more. Returns: result

generate_robots_metaB

Build a robots meta tag from directives, with the resulting tag and an explanation of what it permits.

Inputs: index, follow, noarchive, nosnippet, +4 more. Returns: object

generate_robots_txtC

Generate a robots.txt. Optionally block the major AI training crawlers.

Inputs: allow_paths, crawl_delay, sitemap_url, disallow_paths, +1 more. Returns: result

keyword_densityC

Word and phrase frequency for a body of text, with a density warning.

Inputs: text (required), top_n. Returns: object

readability_scoreB

Flesch Reading Ease and grade level for a body of text.

Inputs: text (required). Returns: object

serp_previewA

Preview how a result will render in Google, including truncation.

Inputs: url (required), title (required), description (required). Returns: object

slugifyB

Turn a title into a clean URL slug.

Inputs: text (required), max_length, keep_stopwords. Returns: object

validate_json_ldA

Validate a JSON-LD block: parse it, check required Schema.org fields, and flag the things that commonly cause a rich-result warning.

Inputs: content (required). Returns: object

validate_robots_txtA

Validate a robots.txt and surface the mistakes that actually cause damage.

Inputs: content (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    B3.1/5.0

    Scored across 18 tools

    Disambiguation4/5

    Each tool targets a distinct SEO asset or action, making most selections unambiguous. Some overlap exists between check_title_length/check_description_length and serp_preview, but the descriptions clarify the different outputs. No tools are redundant.

    Naming Consistency4/5

    The naming is mostly consistent with a generate_/check_/validate_ pattern, and all names use snake_case. Exceptions like slugify, keyword_density, and readability_score deviate slightly but remain intuitive and readable.

    Tool Count4/5

    At 18 tools, the count is slightly above the typical 3-15 range but justified by the breadth of SEO functionality. Each tool serves a distinct purpose, though a few could be consolidated or omitted without major loss.

    Completeness3/5

    The toolkit covers many core SEO tasks: meta generation, robots handling, common schemas, and content analysis. However, significant gaps remain, such as sitemap generation, redirect handling, and a broader set of schema types (e.g., Product, Recipe). These missing pieces limit full lifecycle coverage.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • seo-audit-mcp

      cyber-kani
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to perform instant SEO audits, check robots.txt, sitemaps, and AI crawler access for any URL without API keys.
      MIT

    • google-seo-mcp

      Akxan
      A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to diagnose and fix technical SEO, content, and generative engine optimization issues by providing 72 tools that integrate Google Search Console, Google Analytics 4, PageSpeed Insights, structured data, llms.txt, WordPress, and GitHub.
      72
      14 npm
      27
      MIT

    • seo-agent

      ahmadaimee
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to access self-hosted SEO data and workflows, including keyword research, rank tracking, competitor insights, backlinks, site audits, and AI visibility.
      MIT