AgentMail

Creates new email inboxes on-demand via REST API without requiring domain verification for agentmail.to subdomains. AgentMail provisions a fully functional SMTP/IMAP-capable email address (e.g., hello@agentmail.to) in milliseconds by allocating a new mailbox on shared or dedicated IP infrastructure and immediately exposing it via API endpoints. The provisioning is synchronous—agents receive a ready-to-use email address in the API response without waiting for DNS propagation or verification steps.

Receives inbound SMTP emails to provisioned inboxes and exposes them via REST API with automatic conversation threading. AgentMail's SMTP server accepts emails, stores them with metadata (sender, recipient, timestamp, subject, body), and groups related messages into threads using standard email headers (In-Reply-To, References, Subject line matching). Agents retrieve emails via API calls that return individual messages or full conversation threads, with support for pagination and filtering by sender/date/label.

Provides dedicated IP addresses for email sending on Startup tier and above, improving email deliverability and reputation. Instead of sharing IP pools with other users, agents get exclusive IPs for their inboxes. Dedicated IPs are configured with proper reverse DNS (PTR records) and can be warmed up gradually to build sender reputation. Startup tier includes 1 dedicated IP; additional IPs available for additional cost (exact pricing not documented).

Exposes AgentMail capabilities via MCP (Model Context Protocol) server, allowing LLM-based agents and AI systems to interact with email inboxes as tools. The MCP server implements AgentMail's API as MCP resources and tools, enabling agents built on Claude, other LLMs, or MCP-compatible frameworks to create inboxes, send/receive emails, and manage labels without direct API calls. MCP integration details (exact tools exposed, resource schema) are not documented.

Manages suppression lists (bounce lists, unsubscribe lists, complaint lists) to improve email deliverability and compliance. Agents can add email addresses to suppression lists to prevent sending to invalid or unsubscribed addresses. AgentMail automatically adds bounced addresses and complaint addresses to suppression lists. Suppression list API and management details are not fully documented.

Provides IMAP and SMTP relay access to AgentMail inboxes, allowing agents to use standard email clients or protocols instead of the REST API. Agents can configure email clients (Outlook, Thunderbird, etc.) or custom IMAP/SMTP clients to connect to AgentMail inboxes using standard credentials. IMAP relay enables reading emails and SMTP relay enables sending emails via standard protocols. Relay configuration details and supported IMAP/SMTP extensions are not documented.

Provides official Python and TypeScript SDKs for AgentMail API with type-safe interfaces and convenience methods. SDKs abstract REST API details, handle authentication, and provide typed objects for inboxes, emails, threads, etc. SDKs support async/await patterns (TypeScript) and async methods (Python), enabling non-blocking I/O in agent systems. SDK documentation and API reference are provided, but exact SDK features and coverage are not fully detailed.

Provides a command-line interface (CLI) tool for managing AgentMail inboxes without using the API or SDKs. Agents can create inboxes, send emails, read messages, and manage labels from the terminal using CLI commands. CLI tool is useful for scripting, automation, and quick testing. Exact CLI commands and options are not documented.

Enables multiple team members to access and manage shared inboxes. Agents can invite team members to inboxes, assign roles (viewer, editor, admin), and track who performed actions (send, reply, label). Team collaboration features allow non-technical team members to manage inboxes without API access. Team member limits and role-based access control details are not fully documented.

Sends outbound emails from provisioned inboxes via REST API with automatic reply threading. Agents call the send endpoint with recipient, subject, body, and optional in-reply-to message ID; AgentMail constructs proper email headers (In-Reply-To, References, Message-ID) to maintain conversation threading, then routes the email through SMTP infrastructure (shared or dedicated IPs depending on tier) to external recipients. Supports draft creation (emails not yet sent) and scheduled send (mentioned in feature matrix but implementation details unknown).

Delivers email events (new message, reply, etc.) to agent systems via HTTP webhooks in real-time. When an email arrives or is sent from an inbox, AgentMail makes an HTTP POST request to a registered webhook URL with a payload containing the email metadata. Agents can register up to 2 webhook endpoints on free tier (limit increases on paid tiers) and use webhooks to trigger immediate processing rather than polling the API. Webhook retry policy, timeout behavior, and exact event types are not documented.

Provides real-time inbox updates via WebSocket connections, allowing agents to receive live notifications of new emails, replies, and other inbox events without polling. Agents establish a WebSocket connection to AgentMail's server and receive messages as events occur. Exact event types, message format, and connection management (heartbeat, reconnection) are not documented.

Stores email attachments and exposes them via API for retrieval. When an email with attachments arrives, AgentMail extracts and stores the files, then returns attachment metadata (filename, size, MIME type, download URL) in the email object. Agents can download attachments via API endpoint or access them through email retrieval. Storage limits vary by tier (3GB free, custom enterprise), but attachment size limits and supported file types are not documented.

Allows agents to apply labels (tags) to emails for organization and filtering. Agents can assign labels to individual emails or threads via API, then retrieve emails filtered by label. Labels are stored with email metadata and can be used for categorization (e.g., 'urgent', 'spam', 'processed'). Label management API (create, delete, rename labels) is not documented; unclear if labels are predefined or agent-created.

Searches emails by semantic meaning rather than keyword matching. Agents can query inboxes with natural language or semantic queries (e.g., 'emails about billing issues') and AgentMail returns relevant emails. Implementation details are unknown—likely uses vector embeddings or keyword indexing, but exact approach, latency, and accuracy are not documented.

Extracts structured data from email content (e.g., dates, amounts, names, action items). Agents can request data extraction from emails and AgentMail returns parsed fields. Implementation details are unknown—likely uses NLP or pattern matching, but exact approach, supported data types, and accuracy are not documented.

Allows agents to use custom domain names for email addresses instead of agentmail.to subdomains. Agents configure a custom domain (e.g., agent@mycompany.com) by updating DNS records (DKIM, SPF, DMARC) and registering the domain in AgentMail. Once configured, new inboxes can use the custom domain. Custom domain support requires Developer tier ($20/month) or higher; setup process and DNS configuration details are not fully documented.