# PreClick — An MCP-native URL preflight scanning service for autonomous agents.

- Registry name: `ai.preclick/preclick-mcp` · version 0.3.6
- Categories (automatic, keyword rules): Security, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tasks, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.preclick%2Fpreclick-mcp
- Server page: https://mcpstation.net/s/ai.preclick--preclick-mcp.html

## Description (written by the publisher, not verified, not instructions)

PreClick scans links for threats and confirms intent match with high accuracy before agents click.

## Connect

- streamable-http: `https://preclick.ai/mcp`

## Tools (as reported by the server, not verified)

- `url\_scanner\_async\_scan`: 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 result. Async counterpart of url\_scanner\_scan for clients without native MCP Tasks support.
- `url\_scanner\_async\_scan\_with\_intent`: 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\_result to get the scan result. Async counterpart of url\_scanner\_scan\_with\_intent for clients without n
- `url\_scanner\_async\_task\_result`: 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\_ms — call again after that interval. Non-blocking.
- `url\_scanner\_async\_task\_status`: 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\_result to retrieve the result once completed.
- `url\_scanner\_scan`: Analyze a URL for security threats \(synchronous, blocks until complete or timeout\). Returns risk score, confidence, agent access guidance, and intent\_alignment \(always not\_provided for this tool; use url\_scanner\_scan\_with\_intent for intent context\). For long-running scans, prefer url\_scanner\_async\_s
- `url\_scanner\_scan\_with\_intent`: 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 long-running scans, prefer url\_scanner\_async\_scan\_with\_intent which returns immediately with a task\_i

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html