PreClick
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. BASIC USAGE Agent: Hey, PreClick - I want to open this link to book a room. PreClick: ALLOW (low risk + destination matches intent). Agent: Hey, PreClick - I want to open this link to invest in crypto. PreClick: DENY (high risk and/or intent mismatch). Telco Agent: Hey, PreClick - validate this URL for the SMS campaign (intent: Device trade-in promo). PreClick: ALLOW (low risk + intent match).
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- communication
- Source
- Smithery
- Author type
- human
- Updated
- 2026-05-10
Use via MCP
Resolve PreClick from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.