Safe email for AI agents: a mailbox with inbound scanning, outbound checks and human review.
The publisher's own URL. Not a PlugMCP endpoint.
https://api.replylayer.ai/v1/mcp
Claude opens with the name and URL filled in. You still confirm it there.
claude mcp add --transport http ai.replylayer-replylayer https://api.replylayer.ai/v1/mcp
Run in a terminal.
{
"mcpServers": {
"ai.replylayer-replylayer": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.replylayer.ai/v1/mcp"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchSafe email for AI agents: a mailbox with inbound scanning, outbound checks and human review.
README is not crawled yet. No repository on file.
No tool list yet. Remote servers get one after the first health check.