Loading…
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The sitepulsar-mcp MCP server exposes 13 tools, focused primarily on general-purpose capabilities. Its published description reads: "AEO agent-readiness audits for any website". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates sitepulsar-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check sitepulsar-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add sitepulsar-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://sitepulsar-mcp.vercel.app/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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
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-
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
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
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 freshl
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
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 `expa
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 catego
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 c
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 mercha
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). Us
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 sco
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 an
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: check_agent_readiness
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: check_agent_readiness
A tool description tries to alter the model’s use of another tool.
her the heavier run_audit is worth a credit.RecommendationDescriptions must describe only their own tool.
tool: run_audit
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: run_audit
A tool description tries to alter the model’s use of another tool.
id to poll with get_audit. Accepts an optional target_keyword. Spends oneRecommendationDescriptions must describe only their own tool.
tool: get_audit
A tool description tries to alter the model’s use of another tool.
with this; call get_audit_detail only when you need the full per-section breakdoRecommendationDescriptions must describe only their own tool.
tool: get_audit_detail
A tool description tries to alter the model’s use of another tool.
only call after get_audit when you need depth): per-dimension FIND/READ/URecommendationDescriptions must describe only their own tool.
tool: compare_aeo
A tool description tries to alter the model’s use of another tool.
id to poll with get_audit. Spends credits only for freshly-audited URLs;RecommendationDescriptions must describe only their own tool.
tool: get_audit_full
A tool description tries to alter the model’s use of another tool.
t have to chain get_audit → get_audit_detail → get_fixes. Use `expand` toRecommendationDescriptions must describe only their own tool.
tool: search_companies
A tool description tries to alter the model’s use of another tool.
mentioned (use scan_visibility for that). Free, no URL needed. Result: { compaRecommendationDescriptions must describe only their own tool.
tool: probe_agent_discovery
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: probe_ucp_readiness
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: probe_mcp_functional
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: scan_product_page
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: scan_visibility
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: scan_visibility
A tool description tries to alter the model’s use of another tool.
omplementary to search_companies, which finds who agents recommend for a categorRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
/READ/USE). Use check_agent_readiness for a fast read; run_audit for a full async audRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: check_agent_readiness
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: run_audit
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_audit
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_audit_detail
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: compare_aeo
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_fixes
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_audit_full
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_companies
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: probe_agent_discovery
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: probe_ucp_readiness
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: probe_mcp_functional
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: scan_product_page
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: scan_visibility
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.