Вход

Аудиты доступности сайтов для AI (AEO): получение баллов готовности FIND/READ/USE, полные отчеты и сравнение нескольких URL.

давно не проверялся Удалённый · Streamable HTTP Без авторизации Веб и поиск ИИ и модели Безопасность mcp Официальный реестр · 11 просмотров

Что умеет

Аудиты доступности сайтов для AI (AEO): получение баллов готовности FIND/READ/USE, полные отчеты и сравнение нескольких URL.

Перевод каталога (LLM) · показать оригинал автора

SitePulsar AEO audits: fetch FIND/READ/USE agent-readiness scores for any website.

Подключение

Удалённый сервер: клиент обращается по адресу, код на вашей машине не запускается.

Claude Desktop

claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Вставьте блок mcpServers в файл конфигурации своего клиента. Ключи не входят в файл: вместо SET_LOCALLY подставьте свои значения.

{
    "mcpServers": {
        "ai-sitepulsar-mcp": {
            "url": "https://mcp.sitepulsar.ai/mcp"
        }
    }
}

Вызов без установки — через шлюз

Агент вызывает инструменты этого сервера через https://www.n2j.ru/mcphub/mcp: hub_call_tool {"server":"ai-sitepulsar-mcp","tool":"…","arguments":{…}} Ключ не нужен, но сервер N2J ограничивает частоту анонимных вызовов.

https://mcp.sitepulsar.ai/mcp

Инструменты

13 схем · ≈ 2 196 условных токенов

check_agent_readiness

Fast synchronous AEO / agent-readiness read of a single URL: robots and bot access, structured data (schema), and content structure. Returns immediate signals without running a full audit. Use this to triage a page or sanity-check before deciding whether the heavier run audit is worth a credit.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute URL to audit."
        }
    },
    "additionalProperties": false
}

run_audit

Run a full AEO audit of a URL covering FIND, READ, and USE. Async: returns an audit id to poll with get audit. Accepts an optional target keyword. Spends one audit credit per fresh run; a same-URL re-run within 24h reuses the cached audit, uncharged.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute URL to audit."
        },
        "target_keyword": {
            "type": "string",
            "description": "Optional keyword to evaluate against; inferred when absent."
        }
    },
    "additionalProperties": false
}

get_audit

Fetch an audit's status and, when complete, a compact decision-ready SUMMARY: AEO score (overall + FIND/READ/USE), a short summary, the weakest pillar, headline takeaways, and the top fixes. Lead with this; call get audit detail only when you need the full per-section breakdown.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "audit_id"
    ],
    "properties": {
        "audit_id": {
            "type": "string",
            "description": "The audit_id returned by run_audit / compare_aeo (poll until status is completed)."
        }
    },
    "additionalProperties": false
}

get_audit_detail

Full structured per-section breakdown of a completed audit, on demand (only call after get audit when you need depth): per-dimension FIND/READ/USE sub-scores, reputation across AI engines, competitor cluster (named for paid tiers), crawl/schema/robots findings, agentic-readiness + USE functional probes, and rendered-DOM analysis (paid). Typed, sanitized, size-capped (see truncated/dropped sections). Composite score fields listed in experimental fields may change methodology — do not hardcode thresholds. Also surfaces author/E-E-A-T, content freshness, images, hreflang, per-page per-bot access,

Показать схему аргументов
{
    "type": "object",
    "required": [
        "audit_id"
    ],
    "properties": {
        "audit_id": {
            "type": "string",
            "description": "The audit_id returned by run_audit / compare_aeo (poll until status is completed)."
        }
    },
    "additionalProperties": false
}

compare_aeo

Compare AEO posture across multiple URLs (e.g. a brand versus its competitors) on the same FIND/READ/USE pillar scale. Async: returns an audit id to poll with get audit. Spends credits only for freshly-audited URLs; recent audits are reused uncharged.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "urls"
    ],
    "properties": {
        "urls": {
            "type": "array",
            "items": {
                "type": "string"
            },
            "minItems": 2,
            "description": "Absolute URLs to compare."
        }
    },
    "additionalProperties": false
}

get_fixes

Return the prioritized, pillar-tagged (FIND / READ / USE) action plan for a completed audit, deduplicated across sources, with machine-actionable implementation steps included on fixes where available. Use this when you want the to-do list to act on (or hand to a coding agent), rather than the scores or section detail.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "audit_id"
    ],
    "properties": {
        "audit_id": {
            "type": "string",
            "description": "The audit_id returned by run_audit / compare_aeo (poll until status is completed)."
        }
    },
    "additionalProperties": false
}

get_audit_full

One call that returns a completed audit's SUMMARY, full per-section DETAIL, and deduplicated prioritized FIXES together — so you don't have to chain get audit → get audit detail → get fixes. Use expand to trim the payload ('summary' 'detail' 'fixes' 'all'; default 'all'). Same ownership, tier gating, and sanitization as those tools. For an in-progress audit it returns the status so you can keep polling. The detail layer includes Wave-B surfaced sections (author/E-E-A-T, freshness, images, hreflang, per-bot access, Action microformats, OpenAPI sub-metrics, Google Intelligence, product readabili

Показать схему аргументов
{
    "type": "object",
    "required": [
        "audit_id"
    ],
    "properties": {
        "expand": {
            "enum": [
                "summary",
                "detail",
                "fixes",
                "all"
            ],
            "type": "string",
            "description": "Which sections to include; default 'all'."
        },
        "audit_id": {
            "type": "string",
            "description": "The audit_id returned by run_audit / compare_aeo (poll until status is completed)."
        }
    },
    "additionalProperties": false
}

search_companies

Samples the major AI engines for which companies they name for a query (e.g. "best CRM for startups"); returns a consensus shortlist (≤5). Use when you want to know who agents recommend for a category — not where a specific brand is mentioned (use scan visibility for that). Free, no URL needed. Result: { companies[], tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "query"
    ],
    "properties": {
        "query": {
            "type": "string",
            "description": "Natural-language search query (3–200 chars)."
        }
    },
    "additionalProperties": false
}

probe_agent_discovery

Checks selected registries (official MCP registry, PyPI, GitHub) for packages/servers tied to a domain or brand. A discovery-surface check (can agents find your published tooling?), not a visibility check. Use when you want to know whether a brand has discoverable agent/developer artifacts listed where agents look for them. Result: { state, score, tier, hits[], tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute https URL of the target (any public domain)."
        },
        "brand": {
            "type": "string",
            "description": "Optional brand/company name; inferred from the domain when absent."
        }
    },
    "additionalProperties": false
}

probe_ucp_readiness

Inspects /.well-known/ucp to report whether AI shopping agents can transact with the site (presence + advertised capabilities only — never a live purchase). Use when evaluating an e-commerce or merchant site for agentic-commerce readiness. Result: { has ucp profile, capabilities[], score, tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute https URL of the target (any public domain)."
        },
        "brand": {
            "type": "string",
            "description": "Optional brand/company name; inferred from the domain when absent."
        }
    },
    "additionalProperties": false
}

probe_mcp_functional

Discovers a site's advertised MCP endpoint (mcp.json / .well-known) and inspects its declared OAuth/transport posture (advertised, not guaranteed-working — it does not run a full live handshake). Use when checking whether a site exposes a connectable MCP server and what it claims to support. Result: { handshake ok, declared endpoint, declared tool names[], score, tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute https URL of the target (any public domain)."
        },
        "brand": {
            "type": "string",
            "description": "Optional brand/company name; inferred from the domain when absent."
        }
    },
    "additionalProperties": false
}

scan_product_page

Deterministically scores one product page (schema, price, availability, image) 0–100 for shopping-agent readability — no LLM, fully repeatable. Use when you want a precise, single-page readability score for a specific product URL rather than a whole-site audit. Available on Pro+ plans. Result: { result: { readability score, ... }, tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute https URL of the target (any public domain)."
        },
        "brand": {
            "type": "string",
            "description": "Optional brand/company name; inferred from the domain when absent."
        }
    },
    "additionalProperties": false
}

scan_visibility

Live AI-visibility scan for a brand: crawl + reputation sampled across AI engines, returning where that brand is mentioned (any public brand, not just your own). Use when you want to know whether and how a named brand already surfaces in AI answers — complementary to search companies, which finds who agents recommend for a category. Pro+ (LLM cost). Result: { reputation[], tool schema version }.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Absolute https URL of the target (any public domain)."
        },
        "brand": {
            "type": "string",
            "description": "Optional brand/company name; inferred from the domain when absent."
        }
    },
    "additionalProperties": false
}