MCP server for technical SEO audits powered by the detail.web engine: site health score, issues across 8 categories and a GEO (AI-search visibility) sub-score.
Project description
atomno-mcp-seo-audit
MCP (Model Context Protocol) server for technical SEO audits, powered by the detail.web engine. Run a site audit straight from your AI agent in Cursor, Claude Desktop or any MCP client — get a health score, issues across 8 categories, and a GEO (Generative Engine Optimization — visibility in AI search) sub-score.
Why not just ask an LLM to "analyze my site"?
Because a language model guesses — it can't read your TLS certificate's
expiry date, measure response time, parse your sitemap.xml, or detect that
GPTBot is blocked in robots.txt. Without tools it hallucinates from the URL;
with browsing it eyeballs one rendered page. This server measures: real HTTP
requests, security headers, redirect chains, structured-data validation — and
returns a deterministic score (same site → same number), reproducible enough
to put in a client report. Think of it as the instrument; the LLM is the analyst
that interprets the readout. Best results come from the two together.
What you get
audit_site(url, depth=1, lang="ru")— one call returns:- health score
0–100(higher is better) and a letter gradeA–F; - issues grouped by category (security, SEO & indexing, performance, GEO, …),
each with status
pass / warn / fail; - a short human-readable summary.
- health score
audit_diff(url, lang="ru")— re-audits a site and compares it to the previous run: health/score delta and which checks got worse or better. The first call stores a baseline. This is something a one-off LLM question can't do — track a site over time. Stateful PRO feature (needs an API key).list_checks(lang="ru")— the full catalogue of engine checks grouped by category, with afree/PRObadge on each — so you (and the agent) can see exactly what the free tier covers and what PRO unlocks.explain_issue(check_id, lang="ru")— a deep-dive on a single check: why it matters and how to fix it. Pass acheck_idfromaudit_siteorlist_checks. Title and category are localized; detailed advice is currently in Russian (theadvice_langfield reports this).validate_robots(content, lang="ru")— paste arobots.txtand get back syntax issues, whether aSitemap:directive is present, whether CSS/JS is blocked from render bots, and which AI crawlers (GPTBot, ClaudeBot, …) are explicitly blocked. No fetch — validates the text you provide.check_sitemap(url, lang="ru")— fetches a sitemap by URL and reports its format (urlset/sitemapindex), URL count and common problems (404, non-XML content type,http://links, missing<lastmod>, the 50k-per-file limit). The fetch is SSRF-guarded on the server.build_jsonld(type, fields, lang="ru")— generates a ready-to-paste schema.org JSON-LD<script>(Organization, LocalBusiness, Article, Product, FAQPage, BreadcrumbList, WebSite) and tells you which required/recommended fields are missing. It never invents data — only what you pass in.build_meta(fields, lang="ru")— generates<head>meta tags (title, description, canonical, Open Graph, Twitter Card) and validates the title (50–60 chars) and description (120–160 chars) lengths.
Free vs PRO
| Free (no key) | PRO (with API key) | |
|---|---|---|
| Checks | core technical basics | 40+ deeper checks (E-E-A-T, Schema.org, Goldmine title) |
| GEO | 4 GEO signals | GEO readiness sub-score + deep GEO checks |
| Crawl | single page | deep-crawl up to 20 pages (depth=2/3) |
The audit engine itself stays on the server — this package is a thin client (HTTP calls + formatting only).
Install
uvx atomno-mcp-seo-audit
Or add to your MCP client config (mcp.json):
{
"mcpServers": {
"seo-audit": {
"command": "uvx",
"args": ["atomno-mcp-seo-audit"]
}
}
}
Configuration
All via environment variables:
| Variable | Default | Purpose |
|---|---|---|
DETAILWEB_API_BASE |
https://api.detailweb.ru |
Backend base URL |
DETAILWEB_API_KEY |
— | PRO key (dwa_...). Without it → free tier |
DETAILWEB_TIMEOUT |
60 |
HTTP timeout (seconds) |
DETAILWEB_LANG |
ru |
Default issue-title language (ru / en) |
Get a PRO key in the detail.web dashboard → Account → API keys.
Example
"Audit https://example.com"
The agent calls audit_site("https://example.com") and gets back the health
score, grade and the list of issues to fix.
License
MIT © atomno-labs. The open-source client talks to a proprietary hosted backend.
🇷🇺 На русском
MCP-сервер технического SEO-аудита на движке detail.web. Запускайте аудит прямо из ИИ-агента (Cursor, Claude Desktop и любой MCP-клиент): health-score, проблемы по 8 категориям и GEO-суб-балл (видимость в ИИ-поиске — ChatGPT, Perplexity, AI Overviews).
Чем отличается от «спросить нейросеть». Языковая модель гадает: она не
прочитает срок вашего SSL-сертификата, не измерит время ответа, не распарсит
sitemap.xml и не увидит, что GPTBot заблокирован в robots.txt. Этот сервер
измеряет — настоящие HTTP-запросы, заголовки, редиректы, микроразметка — и даёт
детерминированный score (тот же сайт → то же число), пригодный для отчёта
клиенту. Это прибор; нейросеть — аналитик, который читает показания. Лучше всего
работает связка.
Инструменты: audit_site (аудит + score + GEO), audit_diff (что
изменилось с прошлой проверки — stateful PRO), list_checks (каталог
проверок free/PRO), explain_issue (почему важно + как исправить),
validate_robots, check_sitemap, build_jsonld, build_meta.
Установка:
uvx atomno-mcp-seo-audit
В конфиге MCP-клиента (mcp.json):
{
"mcpServers": {
"seo-audit": {
"command": "uvx",
"args": ["atomno-mcp-seo-audit"],
"env": { "DETAILWEB_LANG": "ru" }
}
}
}
PRO-режим (40+ глубоких проверок, GEO-суб-балл, deep-crawl до 20 страниц):
добавьте DETAILWEB_API_KEY (dwa_…) в env. Ключ — в кабинете detail.web →
Аккаунт → API-ключи. Без ключа работает бесплатный тариф (базовые проверки,
одна страница). Полное описание инструментов и настроек — в английской версии
выше.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file atomno_mcp_seo_audit-0.4.0.tar.gz.
File metadata
- Download URL: atomno_mcp_seo_audit-0.4.0.tar.gz
- Upload date:
- Size: 21.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
39724652038750c6c8a419c84b282cae1609c03920bed3710510ac0a228eb7c2
|
|
| MD5 |
bd83f02d3522cc05a45a1133bf4ae4b8
|
|
| BLAKE2b-256 |
3c52ffebac11e3a7de52990411da3057b2c00f9e3105122026c1c0815d21d657
|
File details
Details for the file atomno_mcp_seo_audit-0.4.0-py3-none-any.whl.
File metadata
- Download URL: atomno_mcp_seo_audit-0.4.0-py3-none-any.whl
- Upload date:
- Size: 19.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
936d55d4014c5da5c64330026187dd768562f01f84c1ff09ff616ee3a5f630ae
|
|
| MD5 |
3186167444cf2811886903d4b9599bd2
|
|
| BLAKE2b-256 |
d2edeb1903582618f3b74277902b82f279eacfb8f8c85038816c3b09f711e010
|
