Outtake Flash is answering right now. Last checked 8 min ago.
Tells your agent if a link is safe before it clicks, signs in or pays.
Today is the operative word: we check Outtake Flash every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add flash --transport http https://armor.outtake.ai/mcp
https://armor.outtake.ai/mcp
[mcp_servers.flash]
url = "https://armor.outtake.ai/mcp"
{
"mcpServers": {
"flash": {
"url": "https://armor.outtake.ai/mcp"
}
}
}
{
"servers": {
"flash": {
"type": "http",
"url": "https://armor.outtake.ai/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://armor.outtake.ai/mcp | streamable-http | sign-in | 423 ms | 8 min ago |
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
Check a seller's wallet before your agent pays it: ok, careful or stop. Free, no key.
Before your agent sets out, ask whether the site will let it in
Check a vendor (name, domain, email) for fraud signals and sanctions before an agent pays it.
Your agent already broke this three times. ChangeBook tells it before the fourth.
Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them.
Check a tx, EIP-712 payload, text or Base token before your agent signs. Paid per call over x402.
Answers built from our own checks of this server.