SendGuard is answering right now. Last checked 3 min ago. It exposes 1 tools.
Check an email before your AI agent sends it: allow, review or block with reasons.
Nothing serious here today
Today is the operative word: we check SendGuard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add preflight --transport http https://api.sendguard.ai/mcp{
"mcpServers": {
"preflight": {
"url": "https://api.sendguard.ai/mcp"
}
}
}[mcp_servers.preflight]
url = "https://api.sendguard.ai/mcp"{
"mcpServers": {
"preflight": {
"url": "https://api.sendguard.ai/mcp"
}
}
}{
"mcpServers": {
"preflight": {
"url": "https://api.sendguard.ai/mcp"
}
}
}Available tools 1
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
preflight_email
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.sendguard.ai/mcp | streamable-http | answering | 640 ms | 3 min ago |
Alternatives to SendGuard
same job, measured the same wayCheck an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Check whether an email address is real and will accept mail before you send to it.
namailu.cz gives your AI agent its own email inbox: read and send mail over MCP, with OAuth.
Safe email for AI agents: a mailbox with inbound scanning, outbound checks and human review.
Check emails before you send, and get a $1 SPF/DKIM/DMARC fix plan for your domain. Pay per call.
Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.
Design on-brand emails with your AI, preview them in chat, and send through server-side guardrails.
Your agent's own email address: read, search, send, reply, draft and wait for mail.
SendGuard — questions
Answers built from our own checks of this server.