A short-lived cache, not an archive
ModMail proxies IMAP and SMTP. Message bodies are held only in a temporary cache that expires minutes after you stop using the tab. The durable copy stays with your provider.
Security & privacy
An email assistant sits on the most sensitive corpus a business owns. ModMail is designed so that giving it access is a bounded decision: what it can reach, how long anything is held, and what it may do without you are all explicit — and the defaults are the cautious ones.
ModMail proxies IMAP and SMTP. Message bodies are held only in a temporary cache that expires minutes after you stop using the tab. The durable copy stays with your provider.
Mailbox passwords, OAuth refresh tokens and model keys are encrypted with AES-256-GCM under a key that lives in the process environment, never in the database. A dump of the tables on its own is useless.
Every tool call is authorised server-side against your permission level, and the model cannot talk its way past it. Sending, replying and forwarding need your approval in the UI by default. The one exception is an agent you explicitly set to Acts: it may send inside the caps you gave it, every send is logged, and turning it back to Drafts stops it immediately.
The app ships no third-party analytics or advertising scripts on authenticated pages, and remote images in message HTML are served through a sandboxed frame rather than fetched with your session.
Each user has one of two levels. Read lets the assistant see the message you have open and answer questions about it; it can draft, but it cannot touch the mailbox. Act adds the tools — labelling, filing, scheduling, preparing a reply in the composer. In both levels the send action itself is a UI step the model has no access to, and the server enforces that independently of what the model believes its instructions are.
The reason is adversarial, not technical: the most dangerous message in an AI mailbox is not one you wrote badly, it is one a stranger wrote well. A model that can be persuaded by the content it reads is a model that can be persuaded to send money, and an approval gate is the only control that survives that.
| Data | Where it lives | Lifetime |
|---|---|---|
| Message bodies | Short-lived server cache | Minutes after the tab closes |
| Your mail archive | Your provider (Gmail, Outlook, IMAP) | Unchanged — never migrated |
| Mailbox passwords and OAuth tokens | Encrypted in the database (AES-256-GCM) | Until you delete the account |
| Model API keys | Encrypted per user, per provider | Until you replace or remove them |
| Agent run logs | Database, tied to your user | Kept so you can audit what ran |
When the assistant answers a question, the relevant part of the open message goes to the provider whose key you configured — OpenAI, Anthropic, Google, OpenRouter, DeepSeek or your own endpoint. That provider’s terms then apply to that request, which is precisely why the key is yours: you choose the vendor, you hold the contract, and you can move to a local model on Ollama, LM Studio or vLLM when a thread must not leave your network at all.
Security reports go to team@modernlisim.com. Include the mailbox or account affected and a timestamp; we would rather hear about a suspicious interaction twice than not at all.