Let Claude Code work through email.

A task does not always arrive as a prompt in the terminal. It may arrive as an email, continue in a reply or include a file somebody needs you to inspect. A dedicated Robotomail address lets Claude Code work with that conversation without sharing a personal inbox.

Use a mailbox for a project or role, such as collecting bug reports or requesting clarification from a collaborator. Keep the approval boundary clear: reading a message and proposing a reply are different from sending one or changing production code.

Remote MCP exposes email actions to Claude Code. Use this when you want Claude to list, read and send messages on request. Follow the Claude Code MCP instructions for the supported connection and authentication flow.

The Claude Code channel brings incoming messages into a running session. The Robotomail plugin connects to the event stream and exposes reply tools. This setup has its own runtime and client-version requirements; use the channel guide before installing it.

Avoid configuring duplicate connections with different credentials for the same mailbox. Choose one clear setup first, test it, then add the other transport only if your workflow needs it.

1. Create your Robotomail account and choose the mailbox address for the project. Complete email verification before sending.
2. Choose remote MCP or the channel guide. Follow the current documented authorization or API-key configuration for that path.
3. Restrict the mailbox access where supported and keep credentials in the configured secret storage.
4. Ask Claude to list the available mailbox and read a test message. Review any tool permission request before proceeding.

For channel installation, the documented plugin commands are:

/plugin marketplace add robotomail/claude-email
/plugin install robotomail@robotomail

Continue with the channel prerequisites and launch instructions. The plugin installation alone does not start a persistent background email agent.

Send an email from your verified signup address to the agent's mailbox. The Free plan supports conversations with that address; use a paid plan for other correspondents. Ask the agent to read the message, identify the sender and subject, and summarize the request before replying. Then approve a reply and inspect the conversation in the receiving client.

Check that the reply comes from the intended mailbox and stays in the same thread. The reply header uses the original RFC Message-ID, not the database ID used to fetch a message. Fetch thread context before following up, and record completed actions outside the model.

Repeat the test with an attachment, an unrelated message and a request the agent should decline. Your agent is ready for a wider workflow when it can handle both the expected path and a safe handoff.

Use a mailbox-scoped API key when the agent only needs one mailbox. Store the key in your runtime's secret storage or a secret manager, and expose it through the integration rather than pasting it into a conversation.

An email can contain instructions designed to change the agent's behavior. Treat the sender, body, links and attachments as untrusted input. Keep private data access and recipient checks in application code. Require approval for sensitive actions and avoid granting broad tools simply because an email requests them.

Robotomail supplies the email interface. The integration and your runtime determine which tools the agent can call and whether it needs your approval. See agent email security.

Ask Claude to summarize a project inquiry and draft a clarification question. Or have it inspect an incoming bug report, identify the missing reproduction steps and prepare a reply for approval.

For longer running workflows, decide what happens when the session closes or reconnects. Store task state outside the chat and use the messages API to reconcile work after a disconnect. Keep production changes, purchases and disclosure of private project data behind explicit authorization.