Your agent stack. A real email address.

Connect the tools you already use to a mailbox that can send, receive and reply. Choose a setup path, then test one conversation.

Start with your runtime. Use the same mailbox API as the workflow grows.

Connect an agent

Claude Code

Use remote MCP for email tools, or the Claude Code channel for live incoming messages in a running session. Build with Claude Code.

OpenClaw

Give an OpenClaw workflow a dedicated address and the Robotomail skill. Keep the API key in the runtime's secret storage. Build with OpenClaw.

Hermes

Connect the Robotomail skill to a Hermes runtime and use a mailbox for ongoing tasks and follow-up conversations. Build with Hermes.

Grok Bot

Connect Grok Bot through remote MCP, approve access in your browser and attach Robotomail to the conversation. Build with Grok Bot.

Muse

Give Muse access to a mailbox through a custom REST connector and a mailbox-scoped API key. Build with Muse.

Build your own integration

REST API. Create mailboxes, send messages, retrieve threads and handle inbound events from your own service. Explore the email API.

SDKs. Use the documented Python and TypeScript clients when you prefer typed helpers to raw HTTP. Open the SDK reference.

MCP. Connect a compatible tool-using client to Robotomail's remote MCP server. Follow the setup for your client and authorize only the access it needs. MCP setup.

Agent skill. Give your runtime the documented API conventions and workflow instructions. A skill teaches the interface; it does not contain your credentials. Read the Robotomail skill.

CLI. Inspect mailboxes and messages or exercise the API during development. CLI reference.

Test a complete conversation

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.

Keep access specific to the task

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.

Common questions

No. Use an agent or application that can call the REST API, an SDK or compatible MCP tools. Your runtime controls model selection and the workflow.

Continue building

Give your agent a way to reply

Start with one mailbox. Build the workflow you need.

Create a mailbox

Choose a mailbox, connect your agent, then test a conversation.