Loading…
Read-only heritage travel search covering 500+ UNESCO World Heritage destinations by region and intent.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month 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 wonders-mcp MCP server exposes 4 tools, focused primarily on general-purpose capabilities. Its published description reads: "Read-only heritage travel search covering 500+ UNESCO World Heritage destinations by region and intent". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates wonders-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" 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 wonders-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add wonders-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://www.machupicchu.org/wp-json/wonders-mcp/v1/jsonrpcStreamable 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.
Search the destination taxonomy by keyword, matching against destination names, slugs and descriptions (this is taxonomy search, not article full-text search). Returns up to `limit` matches as objects
Retrieve full metadata for a single destination by its `slug`. Returns an object with the geographic `hierarchy` (ancestor regions), a click-through `url`, `cite_as` (the canonical source link), total
Enumerate all destinations nested under a macro-region. `region` must be a valid region slug (e.g. "south-america", "mediterranean-europe", "world-heritage"); browse the wonders://taxonomy resource to
Fetch editorial articles for a destination, filtered by a single travel intent. `destination_slug` must be a valid destination slug (obtain it from search_destinations or get_destination). `intent` mu
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: search_destinations
A tool description tries to alter the model’s use of another tool.
ug` required by get_destination and get_posts_by_intent.RecommendationDescriptions must describe only their own tool.
tool: get_destination
A tool description tries to alter the model’s use of another tool.
all this before get_posts_by_intent to see which intents are actually populated forRecommendationDescriptions must describe only their own tool.
tool: get_posts_by_intent
A tool description tries to alter the model’s use of another tool.
(obtain it from search_destinations or get_destination). `intent` must be exactly oRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
edge graph. Use search_destinations to find places, get_destination for full metadaRecommendationDescriptions 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.
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.