mcp-seo-audit
PYPI · ATOMNO-MCP-SEO-AUDIT · SCANNED SEP 13
Technical SEO site audit MCP: health score, issues, robots, sitemap, JSON-LD.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 22 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 11 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1589 tokens (~198/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the mcp-seo-audit server?
mcp-seo-audit runs locally as a PyPI package, launched with uvx atomno-mcp-seo-audit. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · atomno-mcp-seo-audit
claude mcp add atomno-mcp-mcp-seo-audit -- uvx atomno-mcp-seo-audit
{
"mcpServers": {
"atomno-mcp-mcp-seo-audit": {
"command": "uvx",
"args": [
"atomno-mcp-seo-audit"
]
}
}
} {
"servers": {
"atomno-mcp-mcp-seo-audit": {
"command": "uvx",
"args": [
"atomno-mcp-seo-audit"
]
}
}
} codex mcp add atomno-mcp-mcp-seo-audit -- uvx atomno-mcp-seo-audit
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"atomno-mcp-mcp-seo-audit": {
"type": "local",
"command": [
"uvx",
"atomno-mcp-seo-audit"
],
"enabled": true
}
}
} openclaw mcp add atomno-mcp-mcp-seo-audit --command uvx --arg atomno-mcp-seo-audit
mcp_servers:
atomno-mcp-mcp-seo-audit:
command: "uvx"
args: ["atomno-mcp-seo-audit"] {
"McpServers": {
"atomno-mcp-mcp-seo-audit": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"atomno-mcp-seo-audit"
]
}
}
} assistant mcp add atomno-mcp-mcp-seo-audit -t stdio -c uvx -a atomno-mcp-seo-audit
{
"mcpServers": {
"atomno-mcp-mcp-seo-audit": {
"command": "uvx",
"args": [
"atomno-mcp-seo-audit"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −2
- Stability: pass → 0.83 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 6 Sept 26 0
- Security disclosure: unverified → fail ▼ functional
- 5 Sept 26 −2
- Security disclosure: fail → unverified ▼ functional
- Stability: pass → 0.80 functional
- 4 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 13 Sept 2026 · Analysed pypi/atomno-mcp-seo-audit@0.4.7
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 22 packages
| Packages resolved | 22 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_diff ~172
Сравнить сайт с прошлой проверкой: что улучшилось, что деградировало. Прогоняет свежий аудит и сопоставляет с предыдущим сохранённым снимком того же URL: дельта health/score и какие именно проверки стали хуже/лучше. Это то, чего разовый вопрос к LLM не умеет — отслеживание сайта во времени. Первый вызов сохраняет базовую точку (сравнивать ещё не с чем). Stateful PRO-функция: нужен DETAILWEB_API_KEY — без него available=false и подсказка про PRO.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Язык заголовков: 'ru' или 'en'. |
| url | string | yes | Полный URL сайта, например https://example.ru |
Structured output declared, but exposes no named fields.
No examples provided.
audit_site ~272
Прогнать технический SEO-аудит сайта — реальными измерениями, не догадкой. Делает настоящие HTTP-запросы и проверяет факты, которые языковая модель не может узнать «из головы»: срок SSL-сертификата, security-заголовки (HSTS, защита от clickjacking), redirect-chain, robots.txt/sitemap.xml, микроразметку, доступ ИИ-краулеров. Возвращает ДЕТЕРМИНИРОВАННЫЙ health-score (0-100, выше = лучше) — тот же сайт даёт то же число, — буквенную оценку, список проблем по категориям и (для PRO) GEO-суб-балл. Без ключа — free-тариф. Используй, чтобы получить твёрдые факты, а затем объясни их пользователю.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | integer | – | Глубина: 1=одна страница, 2=≈8 стр, 3=≈20 стр (deep — только PRO). |
| lang | string | – | Язык заголовков проверок: 'ru' или 'en'. |
| url | string | yes | Полный URL сайта, например https://example.ru |
Structured output declared, but exposes no named fields.
No examples provided.
build_jsonld ~150
Сгенерировать готовый блок JSON-LD schema.org из переданных полей. Не выдумывает данные — кладёт только то, что передали, и подсказывает, каких обязательных/рекомендованных полей не хватает. Возвращает готовый <script>.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | object | yes | Поля схемы. Для FAQPage — faq=[{question, answer}]; для BreadcrumbList — items=[{name, url}]. |
| lang | string | – | Язык сообщений: 'ru' или 'en'. |
| type | string | yes | Тип schema.org: Organization, LocalBusiness, Article, Product, FAQPage, BreadcrumbList, WebSite. |
Structured output declared, but exposes no named fields.
No examples provided.
build_meta ~108
Сгенерировать <head>-мета-теги (title, description, canonical, Open Graph, Twitter Card) и проверить длины title (50–60) и description (120–160). Возвращает готовый блок тегов.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | object | yes | title, description, url (canonical), image (og 1200×630), site_name, type, twitter_card, locale. |
| lang | string | – | Язык сообщений: 'ru' или 'en'. |
Structured output declared, but exposes no named fields.
No examples provided.
check_sitemap ~105
Скачать и разобрать sitemap по URL: формат (urlset/index), число URL и частые проблемы (404, не-XML, http-ссылки, отсутствие lastmod, превышение лимита 50 000). Фетч защищён от SSRF на стороне сервера.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Язык сообщений: 'ru' или 'en'. |
| url | string | yes | URL карты сайта, например https://example.ru/sitemap.xml |
Structured output declared, but exposes no named fields.
No examples provided.
explain_issue ~122
Подробно объяснить одну проверку: почему она важна и как её исправить. Принимает check_id из результата audit_site/list_checks. Заголовок и категория локализуются; развёрнутые советы пока на русском (поле advice_lang это сообщает). Для неизвестного id — found=false.
| Name | Type | Req | Description |
|---|---|---|---|
| check_id | string | yes | ID проверки (из audit_site или list_checks), например 'hsts', 'title_quality'. |
| lang | string | – | Язык метаданных: 'ru' или 'en'. |
Structured output declared, but exposes no named fields.
No examples provided.
list_checks ~86
Список всех проверок движка с разбивкой free/PRO по категориям. Помогает понять, что входит в бесплатный тариф, а что — только в PRO, и какие категории покрывает движок (security, SEO, GEO, E-E-A-T и т.д.).
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Язык заголовков: 'ru' или 'en'. |
Structured output declared, but exposes no named fields.
No examples provided.
validate_robots ~119
Проверить содержимое robots.txt: синтаксис, sitemap-директива, блокировка CSS/JS от рендер-ботов и явные запреты ИИ-краулеров (GPTBot, ClaudeBot и т.д.). Передайте текст файла — фетч не выполняется, проверка локальная на бэкенде.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | Содержимое файла robots.txt (вставьте текст целиком). |
| lang | string | – | Язык сообщений: 'ru' или 'en'. |
Structured output declared, but exposes no named fields.
No examples provided.
What is the mcp-seo-audit server?
mcp-seo-audit is listed in the public MCP registry as io.github.atomno-mcp/mcp-seo-audit. Technical SEO site audit MCP: health score, issues, robots, sitemap, JSON-LD. This page covers its PyPI package (atomno-mcp-seo-audit).
Is the mcp-seo-audit server safe to use?
mcp-seo-audit scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 13 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the mcp-seo-audit server expose?
mcp-seo-audit exposes 8 tools: audit_site, audit_diff, list_checks, explain_issue, validate_robots, and 3 more. Their descriptions and schemas cost roughly 1,134 tokens of context every time the server is loaded.
Is the mcp-seo-audit server still maintained?
mcp-seo-audit is still listed as active in the MCP registry. We last reached this channel on 13 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the mcp-seo-audit server under?
mcp-seo-audit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.