Oryah Mail is answering right now. Last checked 10 min ago.
Governed email for agents: Gmail, M365 and IMAP; per-mailbox permissions, send allowlist, audit log
Today is the operative word: we check Oryah Mail 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 10 min ago.
claude mcp add oryah-mail --transport http https://mail-mcp.infinihash.com/mcp
{
"mcpServers": {
"oryah-mail": {
"url": "https://mail-mcp.infinihash.com/mcp"
}
}
}
[mcp_servers.oryah-mail]
url = "https://mail-mcp.infinihash.com/mcp"
{
"mcpServers": {
"oryah-mail": {
"url": "https://mail-mcp.infinihash.com/mcp"
}
}
}
{
"mcpServers": {
"oryah-mail": {
"url": "https://mail-mcp.infinihash.com/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://mail-mcp.infinihash.com/mcp | streamable-http | sign-in | 455 ms | 10 min ago |
Governed email for AI agents (Mailbuttons / mbag.ai): sandbox inboxes, policy gate, audit log.
Persistent memory for AI agents — log and recall conversation context over MCP.
Permission tiers, approval gates, and audit logging for MCP servers - the server is the gatekeeper
Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.
Nostr publishing, queries, and DMs for AI agents, with allowlists, rate limits, and an audit log.
Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
Security gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.
Hosted CRM and task desk for AI agents: per-agent keys, scopes, pause and audit log.
Answers built from our own checks of this server.