{"id":"7bbc6009-dd4b-4b4d-8f89-17b23ea8fb9e","slug":"smithery-cybrlab-ai-preclick","name":"PreClick","description":"PreClick: An intent + security layer for agent browsing that verifies each destination before an agent proceeds, applying analyst-like reasoning, adaptive behavior, and continuous improvement. It enables AI agents and any MCP-compatible client to analyze URLs for malicious content and security threats before navigation.\n\nBASIC USAGE\n\nAgent: Hey, PreClick - I want to open this link to book a room.\nPreClick: ALLOW (low risk + destination matches intent).\n\nAgent: Hey, PreClick - I want to open this link to invest in crypto.\nPreClick: DENY (high risk and/or intent mismatch).\n\nTelco Agent: Hey, PreClick - validate this URL for the SMS campaign (intent: Device trade-in promo).\nPreClick: ALLOW (low risk + intent match).","capabilities":[],"protocols":["MCP"],"safetyScore":86,"overallRank":37.5,"trustScore":null,"trust":null,"source":"SMITHERY","updatedAt":"2026-04-15T00:43:49.323Z"}