For AI agents
Your agent clicks links. Scammers know that.
Autonomous agents open URLs, read inbound messages, and move money — with no instinct for a fake invoice or a spoofed login page. Cautellus gives them one: two MCP tools that return a verdict your agent gates its next action on.
Same detection engine as the Cautellus scanner — scam patterns, brand-impersonation checks, community reports, live threat feeds.
Don't proceed. Don't click, reply, or pay.
Pause and confirm with a human before acting.
No known scam indicators — continue.
Working in three steps
- 1Buy a credit packCheckout takes a minute; your ctl_live_ API key appears immediately after payment.
- 2Connect the MCP serverOne config block in any MCP-compatible client — Claude, or any agent framework.
- 3Let the agent gate on verdictsThe server ships instructions with the handshake, so agents know: danger = stop, warn = ask a human.
Connect in one line
claude mcp add --transport http cautellus https://cautellus.com/api/mcp \ --header "Authorization: Bearer ctl_live_YOUR_KEY"
Any other MCP client: point it at https://cautellus.com/api/mcp with your key in the Authorization header. Full reference on the developer docs.
The tools your agent gets
| scan_url | Verdict + risk score + findings for a link before the agent visits or transacts with it. | 1 credit |
| scan_message | Same analysis for a message, email, or text before the agent acts on it. | 1 credit |
| get_usage | Remaining credit balance and expiry. | Free |
Pay as you go
One-time credit packs — no subscription. Every scan runs a real AI analysis, so there is no free tier.
One-time payment — no subscription. Your API key is issued instantly after checkout. Credits are valid for 12 months from purchase; buying another pack with the same email tops up the same key and resets the clock.
Questions agents' builders ask
How does my AI agent use Cautellus?
Connect the Cautellus MCP server (https://cautellus.com/api/mcp) with your API key in the Authorization header. Your agent then gets scan_url, scan_message, and get_usage as tools it can call before clicking a link, replying to a message, or completing a transaction.
What does a scan return?
A verdict (safe, warn, or danger), a 0-100 risk score, a plain-English summary, and specific findings such as brand impersonation, typosquatting, community scam reports, and threat-feed hits. Agents gate actions on the verdict: danger means do not proceed, warn means confirm with a human.
How much does it cost?
Prepaid credit packs: $10 for 50 scans, $49 for 275, $199 for 1,250. One scan equals one credit; get_usage balance checks are free. One-time payments, no subscription, API key issued instantly after checkout. Credits are valid for 12 months.
Does it work with clients other than Claude?
Yes. The server implements the standard MCP Streamable HTTP transport, so any MCP-compatible client or agent framework can connect with a JSON config pointing at https://cautellus.com/api/mcp.