# PreClick

> Use this tool when you need to verify the security and intent of a URL before navigation, to prevent AI agents from accessing malicious content or security threats. PreClick analyzes URLs and provides an ALLOW or DENY response based on risk level and intent match, enabling safe browsing for AI agents and MCP-compatible clients. It is particularly useful in contexts where agents interact with unknown or untrusted URLs, such as web browsing, SMS campaigns, or online transactions.

Canonical page: https://skillsregistry.net/skills/cybrlab-ai-preclick  
JSON: https://api.skillsregistry.net/v1/skills/cybrlab-ai-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.

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).

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-05-10

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/cybrlab-ai/PreClick)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cybrlab-ai-preclick"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cybrlab-ai-preclick` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cybrlab-ai-preclick/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt