菜单
Operate AgentMail from a shell with the official CLI. Use when the user wants commands for listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output; do not use for SDK code, MCP setup, or framework adapters.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Create, list, inspect, update, or delete AgentMail inboxes through the connected MCP server. Use for ANY inbox lifecycle request — even a quick list-inboxes or a simple delete; deletion safeguards apply regardless of task size. Also use when the user asks for a new agent email address, wants inbox details changed, or removes an inbox; do not use for sending mail (agentmail-send-email), reading or triage (agentmail-check-email), or MCP connection setup (agentmail-mcp).
Draft, send, reply to, or forward email through the connected AgentMail MCP server. Use for ANY request to send, reply to, or forward mail — even a quick one-line send or a simple forward that looks like a single tool call; the sending rules apply regardless of task size. Also use to compose messages, create or schedule drafts for review, or send to named recipients; do not use for reading or triaging mail (agentmail-check-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Architecture patterns for AI agents that communicate over email -- why agents need dedicated inboxes rather than human email accounts, infrastructure/provider tradeoffs, one-inbox-per-agent, two-way conversation loops, human-in-the-loop drafts, WebSocket vs webhook event design, multi-agent topologies, OTP flows, and the threat model (prompt injection, webhook spoofing, credential exposure, data leakage). Use when designing how agents send, receive, and manage email conversations, evaluating whether an agent needs email, or choosing an email provider; do not use for AgentMail SDK method calls or basic send/receive implementation.
Configure or troubleshoot the hosted AgentMail MCP server for Codex, Claude Code, Cursor, or another Streamable HTTP MCP client. Use for installation, OAuth, API-key headers, connection failures, or MCP tool discovery. Do not use when the connection already works and the user just wants to send, check, or manage mail — use the sibling action skills for that.
Deprecated alias of the agentmail skill, kept so existing installs and pinned URLs keep resolving. Prefer installing agentmail; this is an identical generated copy covering AgentMail SDK usage in TypeScript and Python.
| name | agentmail-cli |
| description | Operate AgentMail from a shell with the official CLI. Use when the user wants commands for listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output; do not use for SDK code, MCP setup, or framework adapters. |
Install the CLI and provide the API key through the environment.
npm install -g agentmail-cli
export AGENTMAIL_API_KEY="am_..."
Subcommands for a resource nested under another use a colon, e.g. inboxes:messages, inboxes:threads, pods:inboxes, pods:threads.
agentmail inboxes list
agentmail inboxes get --inbox-id <inbox_id>
agentmail inboxes create --display-name "Support Agent" --username support
agentmail inboxes delete --inbox-id <inbox_id>
Confirm the exact inbox before running the destructive delete command.
agentmail inboxes:messages list --inbox-id <inbox_id>
agentmail inboxes:messages get --inbox-id <inbox_id> --message-id <message_id>
agentmail inboxes:messages send --inbox-id <inbox_id> \
--to "recipient@example.com" \
--subject "Hello" \
--text "Message body"
# HTML body instead of plain text
agentmail inboxes:messages send --inbox-id <inbox_id> \
--to "recipient@example.com" \
--subject "Hello" \
--html "<h1>Hello</h1>"
agentmail inboxes:messages reply --inbox-id <inbox_id> \
--message-id <message_id> \
--text "Reply body"
agentmail inboxes:messages forward --inbox-id <inbox_id> \
--message-id <message_id> \
--to "someone@example.com"
agentmail inboxes:threads list --inbox-id <inbox_id>
agentmail inboxes:threads get --inbox-id <inbox_id> --thread-id <thread_id>
Use a message ID for replies. Fetch the full message before relying on body content.
agentmail inboxes:drafts create --inbox-id <inbox_id> \
--to "recipient@example.com" \
--subject "Pending approval" \
--text "Draft body"
agentmail inboxes:drafts list --inbox-id <inbox_id>
agentmail inboxes:drafts get --inbox-id <inbox_id> --draft-id <draft_id>
agentmail inboxes:drafts send --inbox-id <inbox_id> --draft-id <draft_id>
Pods group inboxes together.
agentmail pods create --name "My Pod"
agentmail pods list
agentmail pods:inboxes create --pod-id <pod_id> --display-name "Pod Inbox"
agentmail pods:inboxes list --pod-id <pod_id>
agentmail pods:threads list --pod-id <pod_id>
agentmail pods:threads get --pod-id <pod_id> --thread-id <thread_id>
agentmail webhooks create --url "https://example.com/webhook" --event-type message.received
agentmail webhooks list
# The CLI requires --feedback-enabled; set it to route bounce/complaint
# notifications to your inboxes.
agentmail domains create --domain example.com --feedback-enabled
agentmail domains verify --domain-id <domain_id>
agentmail domains get-zone-file --domain-id <domain_id>
| Flag | Purpose |
|---|---|
--api-key | Override AGENTMAIL_API_KEY for this call |
--base-url | Point at a non-default API host |
--environment | Select a named environment |
--format | Output format (see below) |
--format-error | Control structured error output |
--transform | GJSON projection of a successful response |
--transform-error | GJSON projection of an error response |
--debug | Verbose request/response logging |
--format accepts: auto (default), pretty, json, jsonl, yaml, raw, explore.
Run agentmail --help and the relevant resource's --help before using an administrative command not covered here.