Loading…
URL preflight scanning service that analyzes links for security threats and verifies alignment with the agent's intended browsing goal.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 8 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 ai.preclick/preclick-mcp MCP server exposes 6 tools, focused primarily on web capabilities. Its published description reads: "URL preflight scanning service that analyzes links for security threats and verifies alignment with the agent's intended browsing goal". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates ai.preclick/preclick-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 ai.preclick/preclick-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add ai.preclick/preclick-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://preclick.ai/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.
Submit a URL for asynchronous security analysis. Returns immediately with a task_id. Poll with url_scanner_async_task_status to check progress, then url_scanner_async_task_result to get the scan resul
Submit a URL with optional user intent for asynchronous security analysis. Returns immediately with a task_id. Poll with url_scanner_async_task_status to check progress, then url_scanner_async_task_re
Retrieve the result of an asynchronous scan task. If completed, returns the full scan result (risk_score, confidence, agent_access_directive, etc.). If still running, returns status with retry_after_m
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: url_scanner_async_scan
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: url_scanner_async_scan
A tool description tries to alter the model’s use of another tool.
progress, then url_scanner_async_task_result to get the scan result. Async counterpart of urRecommendationDescriptions must describe only their own tool.
tool: url_scanner_async_scan_with_intent
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: url_scanner_async_scan_with_intent
A tool description tries to alter the model’s use of another tool.
progress, then url_scanner_async_task_result to get the scan result. Async counterpart of urRecommendationDescriptions must describe only their own tool.
tool: url_scanner_async_task_status
A tool description tries to alter the model’s use of another tool.
t blocking. Use url_scanner_async_task_result to retrieve the result once completed.RecommendationDescriptions must describe only their own tool.
tool: url_scanner_scan
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: url_scanner_scan
A tool description tries to alter the model’s use of another tool.
g scans, prefer url_scanner_async_scan which returns immediately with a task_id for poRecommendationDescriptions must describe only their own tool.
tool: url_scanner_scan_with_intent
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: url_scanner_scan_with_intent
A tool description tries to alter the model’s use of another tool.
g scans, prefer url_scanner_async_scan_with_intent which returns immediately with a task_id for poRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
tools instead: url_scanner_async_scan (or url_scanner_async_scan_with_intent) to submRecommendationDescriptions 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: url_scanner_async_scan
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: url_scanner_async_scan_with_intent
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: url_scanner_scan
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: url_scanner_scan_with_intent
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.
Check the status of an asynchronous scan task. Returns the current task status using native MCP task semantics (working, completed, failed, cancelled) without blocking. Use url_scanner_async_task_resu
Analyze a URL for security threats (synchronous, blocks until complete or timeout). Returns risk score, confidence, agent access guidance, and intent_alignment (always not_provided for this tool; use
Analyze a URL for security threats with optional user intent context (synchronous, blocks until complete or timeout). Returns risk score, confidence, agent access guidance, and intent_alignment. For l