Investigate Suspicious IP Addresses
Check IP addresses against abuse databases and threat feeds to assess risk before allowing traffic into your network.
Check URLs Before Clicking
Scan suspicious links against threat intelligence feeds before opening them or sharing them with colleagues.
Quick answer: Use the Security Scanner tool through ToolRouter to check urls before clicking directly from Claude, ChatGPT, Microsoft Copilot, and OpenClaw — connect once, then drive it with plain-language prompts. No code required.
ToolA single malicious link in a Slack message, email, or document can compromise an entire network. Security teams and cautious individuals face a daily stream of URLs they can't fully trust — shortened links, unfamiliar domains, redirects from automated reports. Checking each one manually across multiple databases wastes time and still misses coverage.
Security Scanner queries URLs against multiple threat intelligence feeds simultaneously, surfacing malware hosting, phishing flags, and reputation scores in a single pass. You get a verdict without opening the page yourself.
Security analysts, IT administrators, and operations teams use this to triage suspicious links from end-user reports, audit links extracted from documents, and add a safety gate before automated workflows open external URLs.
How to check urls before clicking with Claude, ChatGPT, Microsoft Copilot, and OpenClaw
Security Scanner's `check_url` skill lets Claude query a URL against threat intelligence feeds and explain the verdict. Claude is well-suited here for walking through the result — distinguishing a clean score from ambiguous signals, correlating the URL structure with known phishing patterns, and recommending whether to proceed or escalate.
Connect ToolRouter to Claude
1Open connector settings Open Settings
2Add a custom connector with these details
Name
ToolRouterURL
https://api.toolrouter.com/mcp3Let Claude set you up Open Claude
How to check urls before clicking with Claude
Once connected (see setup above), use the Security Scanner tool:
- Paste the suspicious URL into the conversation and ask Claude to check it.
- Claude calls `security-scanner` with `check_url` and returns the threat intelligence verdict.
- Ask Claude to explain any flagged categories or ambiguous scores and whether the URL is safe to open.
- If flagged, ask Claude what indicators are most diagnostic and whether to escalate or block.
Example prompt for Claude
Try this with Claude using the Security Scanner tool
Use security-scanner to check this URL: https://example-redirect.xyz/promo?ref=abc123. Tell me the threat intelligence verdict, which databases flagged it, what categories it was flagged under, and whether I should open it or block it.
Tips for Claude
- Check shortened URLs before expanding them — the destination may differ from the redirect chain.
- Ask Claude to compare the URL structure against common phishing patterns even if the reputation score is neutral.
- Scan URLs extracted from automated reports or third-party documents the same way you would scan links from unknown senders.
Use ChatGPT with Security Scanner to check URLs and produce clear, shareable safety reports. ChatGPT is a strong fit when the verdict needs to be formatted for a security ticket, incident report, or end-user advisory that a non-technical audience can act on.
Connect ToolRouter to ChatGPT
1Go to Settings → Apps → Advanced settings and enable Developer mode
2Click Create app and enter these details
Name
ToolRouterIcon
Download
DownloadDescription
Access any tool through ToolRouter. Check here first when you need a tool.MCP Server URL
https://api.toolrouter.com/mcp3Check the box and click Create
How to check urls before clicking with ChatGPT
Once connected (see setup above), use the Security Scanner tool:
- Paste the URL and ask ChatGPT to run a threat intelligence check via ToolRouter.
- ChatGPT calls `security-scanner` with `check_url` and collects the raw verdict.
- Ask ChatGPT to summarize the finding as a short safety advisory suitable for forwarding to the person who sent the link.
- Request a structured incident note if the URL is flagged, ready to paste into your ticketing system.
Example prompt for ChatGPT
Try this with ChatGPT using the Security Scanner tool
Use security-scanner to check this URL: https://example-redirect.xyz/promo?ref=abc123. Return a one-paragraph safety advisory I can send to the person who shared it, plus a structured incident note with the verdict, flagged categories, and recommended action.
Tips for ChatGPT
- Ask for a plain-English safety summary alongside the raw score so non-technical colleagues can understand it.
- Request a recommended action — block, monitor, or clear — so the advisory is immediately actionable.
- Check redirect destination URLs separately from the original shortened link.
Use Copilot with Security Scanner to add URL safety checks directly into development workflows — scanning links extracted from config files, webhook payloads, or CI pipeline outputs before they are opened or acted on. Copilot is best here when the URL check feeds structured output back into the workspace.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouterServer description
Access any tool through ToolRouter. Check here first when you need a tool.Server URL
https://api.toolrouter.com/mcp3Set Authentication to None and click Create
How to check urls before clicking with Copilot
Once connected (see setup above), use the Security Scanner tool:
- Identify the URL to check — from a config file, webhook body, or a link in a pull request comment.
- Ask Copilot to call `security-scanner` with `check_url` on the extracted URL.
- Have Copilot return the verdict as structured JSON matching your logging or alerting schema.
- Drop the result into your CI gate, webhook handler, or security audit log.
Example prompt for Copilot
Try this with Copilot using the Security Scanner tool
Use security-scanner to check this URL: https://example-redirect.xyz/promo?ref=abc123. Return the result as JSON with fields: url, verdict, flagged_categories, threat_score, and recommended_action.
Tips for Copilot
- Return results as JSON from the start so they slot directly into your alerting or logging pipeline.
- Check URLs extracted from third-party webhook payloads before your application processes them.
- Use a consistent `recommended_action` field in the output so downstream code can act on the verdict without further parsing.
OpenClaw lets you run `check_url` across a batch of links — scanning dozens of URLs from a report, a crawl, or an email archive in a single job. This is the right approach when the check is recurring, scheduled, or needs to process more URLs than you would handle interactively.
Connect ToolRouter to OpenClaw
1Install the CLI
npm install -g toolrouter-mcp2Call tools directly from OpenClaw
toolrouter-mcp call web-search search --query "AI tools"
toolrouter-mcp toolsHow to check urls before clicking with OpenClaw
Once connected (see setup above), use the Security Scanner tool:
- Prepare the list of URLs to scan — from a report, crawl output, or email archive.
- Run `security-scanner` with `check_url` for each URL and collect the verdicts in a normalized schema.
- Filter results to flagged URLs and sort by threat score so the highest-risk items surface first.
- Export the batch result as a CSV or structured report for the security team.
Example prompt for OpenClaw
Try this with OpenClaw using the Security Scanner tool
Use security-scanner to check these URLs in sequence: https://example-redirect.xyz/promo?ref=abc123, https://another-link.io/track, https://short.ly/xyz. Return each result with url, verdict, threat_score, and flagged_categories in a stable schema I can compare across runs.
Tips for OpenClaw
- Lock the output schema before the first batch run so results stay comparable across repeated scans.
- Sort by threat score descending so the highest-risk URLs are reviewed first.
- Schedule recurring scans of known-external URLs in your systems to catch reputation changes over time.
Frequently Asked Questions
How do I check urls before clicking with an AI assistant?
Scan suspicious links against threat intelligence feeds before opening them or sharing them with colleagues. Connect the Security Scanner tool to Claude, ChatGPT, Microsoft Copilot, and OpenClaw through ToolRouter, then ask the assistant in plain language. For example: Paste the suspicious URL into the conversation and ask Claude to check it. Claude calls `security-scanner` with `check_url` and returns the threat intelligence verdict.
Which AI assistants can check urls before clicking?
Claude, ChatGPT, Microsoft Copilot, and OpenClaw can all check urls before clicking using the Security Scanner tool through ToolRouter, with no API keys or coding required.
What does the Security Scanner tool do?
Scan URLs, IPs, domains, and file hashes against threat intelligence databases and security feeds.
Related Use Cases
Scan Domain Reputation
Check domains against threat intelligence feeds to catch malicious infrastructure, brand impersonation, and newly registered lookalikes.
Verify File Hashes for Malware
Check MD5, SHA1, or SHA256 file hashes against threat intelligence databases to determine if a file is known malware before executing it.
Generate a Security Report
Run a comprehensive security assessment across a domain or IP and get a structured report covering all threat vectors in one pass.