Agent Safe is listed as active in the registry but did not answer our last check.
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Agent Safe does not always answer
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add agentsafe --transport http https://agentsafe.locationledger.com/mcphttps://agentsafe.locationledger.com/mcp[mcp_servers.agentsafe]
url = "https://agentsafe.locationledger.com/mcp"{
"mcpServers": {
"agentsafe": {
"url": "https://agentsafe.locationledger.com/mcp"
}
}
}{
"servers": {
"agentsafe": {
"type": "http",
"url": "https://agentsafe.locationledger.com/mcp"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentsafe.locationledger.com/mcp | streamable-http | answering | 1574 ms | 13 min ago |
Alternatives to Agent Safe
same job, measured the same wayEmail safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
Email MCP server for Gmail, Outlook and any IMAP mailbox, hardened against prompt injection
Threat intelligence for AI agents: checks URLs, domains, phones, emails, wallets and IBANs for scams
Email and SMS MCP server for AI agents — 41 tools for inboxes, sending, search, and SMS.
Programmable email inbox for AI agents — JMAP, PoW auth, stdio MCP server.
Agent Safe — questions
Answers built from our own checks of this server.