How do I install the Agentmail CLI skill?

Run npx skillmds@latest add agentmail-to/agentmail-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agentmail CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agentmail CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agentmail CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agentmail CLI?

agentmail-to (@agentmail-to) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agentmail CLI by agentmail-to — Agent Skill

Name: Agentmail CLI
Rating: 4.666666666666667 (3 reviews)
Author: agentmail-to

Agentmail CLI

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.

agentmail-to 518b84f 2 files · 3.8 KB Updated Sep 10, 2026

File contents

AgentMail CLI

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.

Inboxes

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.

Messages and threads

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.

Drafts

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

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>

Webhooks

agentmail webhooks create --url "https://example.com/webhook" --event-type message.received
agentmail webhooks list

Domains

agentmail domains create --domain example.com

# Optional: 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>

Global flags

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

Output formats

--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.

---name: agentmail-clidescription: 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.---# AgentMail CLIInstall the CLI and provide the API key through the environment.```bashnpm install -g agentmail-cliexport AGENTMAIL_API_KEY="am_..."```Subcommands for a resource nested under another use a colon, e.g. `inboxes:messages`, `inboxes:threads`, `pods:inboxes`, `pods:threads`.## Inboxes```bashagentmail inboxes listagentmail inboxes get --inbox-id <inbox_id>agentmail inboxes create --display-name "Support Agent" --username supportagentmail inboxes delete --inbox-id <inbox_id>```Confirm the exact inbox before running the destructive delete command.## Messages and threads```bashagentmail 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 textagentmail 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.## Drafts```bashagentmail 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>```## PodsPods group inboxes together.```bashagentmail pods create --name "My Pod"agentmail pods listagentmail 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>```## Webhooks```bashagentmail webhooks create --url "https://example.com/webhook" --event-type message.receivedagentmail webhooks list```## Domains```bashagentmail domains create --domain example.com# Optional: route bounce/complaint notifications to your inboxes.agentmail domains create --domain example.com --feedback-enabledagentmail domains verify --domain-id <domain_id>agentmail domains get-zone-file --domain-id <domain_id>```## Global flags| 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 |## Output formats`--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.

Frequently asked questions