atomic-mail-agentic
Let your agents read, send, and react to email autonomously, without human involvement
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Atomic-Mail/atomic-mail-agentic with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Atomic-Mail/atomic-mail-agentic'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/atomic-mail--atomic-mail-agentic)HTML
<a href="/listings/atomic-mail--atomic-mail-agentic"><img src="/api/listings/atomic-mail--atomic-mail-agentic/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
π¬ Ready Prompt (any agent)
Read the instruction at https://atomicmail.ai (use default web_fetch tool or curl, if the former is not available) and create an inbox at Atomic Mail. Before creating ask for my preferred username. Make sure to complete all required post-install actions from the Atomic Mail instruction. Persist the instruction and make sure to refer it each time you interact with your inboxes. Usually standalone agents (e.g. Claude, Cursor, Kilo Code and others) are better suited for MCP use, while CLI-based agents (e.g. Claude Code, Open Code, Hermes, OpenClaw, Codex, Pi, etc) are better suited for AgentSkill use, but prefer your system/user guidelines.
<p align="center"> </p>
π MCP (stdio)
Add this to your MCP host config (or just ask your agent to do that):
{
"mcpServers": {
"atomicmail": {
"command": "npx",
"args": ["-y", "@atomicmail/mcp-github"]
}
}
}Then restart the host and ask your agent to create an inbox.
π¦ ClawHub
openclaw skills install atomicmail
π©π» Hermes
hermes skills install clawhub/atomicmail
π» AgentSkill
npx --package=@atomicmail/agent-skill-github atomicmail register --username "myagent" --watch scheduled npx --package=@atomicmail/agent-skill-github atomicmail jmap_request --ops-file list_inbox.json npx --package=@atomicmail/agent-skill-github atomicmail help
βοΈ REST API
*For custom connectors and advanced logic only*
Refer to documentation: [docs/rest-auth.md](docs/rest-auth.md).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md Β· README Β· 208 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- <p align="center">
- <a href="https://github.com/Atomic-Mail/atomic-mail-agentic/actions"><img src="https://shieldcn.dev/badge/CI-success-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="CI success"/></a>
- <a href="https://github.com/Atomic-Mail/atomic-mail-agentic/releases"><img src="https://shieldcn.dev/badge/version-0.3-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="version 0.3"/></a>
- <a href="https://atomicmail.ai"><img src="https://shieldcn.dev/badge/website-atomicmail.ai-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="website atomicmail.ai"/></a>
- <a href="https://dashboard.atomicmail.ai"><img src="https://shieldcn.dev/badge/dashboard-sign%20in-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="dashboard sign in"/></a>
- <a href="https://docs.atomicmail.ai/"><img src="https://shieldcn.dev/badge/docs-guide-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="docs guide"/></a>
- <a href="https://github.com/Atomic-Mail/atomic-mail-agentic/issues"><img src="https://shieldcn.dev/badge/issues-open-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="issues open"/></a>
- <a href="https://clawhub.ai/atomicmail/atomicmail"><img src="https://shieldcn.dev/badge/ClawHub-skill-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="ClawHub skill"/></a>
- <a href="https://hermes-agent.nousresearch.com/docs/developer-guide/creating-skills"><img src="https://shieldcn.dev/badge/Hermes-skill-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="Hermes skill"/></a>
- <a href="https://marketplace.dify.ai/plugin/atomicmail/atomicmail"><img src="https://shieldcn.dev/badge/Dify-plugin-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="Dify plugin"/></a>
- <a href="https://registry.modelcontextprotocol.io/?q=atomic-mail"><img src="https://shieldcn.dev/badge/MCP-registry-5BE481.svg?split=true&labelColor=000000&color=5BE481&valueColor=000000&labelTextColor=FFFFFF&height=32&fontSize=16" alt="MCP registry"/></a>
- </p>
- <p align="center">
- <img src="assets/Logo.png" alt="Atomic Mail Agentic Logo" />
- </p>
- # Atomic Mail Agentic
- **Give your agent a real inbox**
- <p align="center">
- <a href="https://dashboard.atomicmail.ai">Dashboard</a> Β·
- <a href="https://atomicmail.ai">Website</a> Β·
- <a href="https://docs.atomicmail.ai/">Docs</a> Β·
- <a href="https://github.com/Atomic-Mail/atomic-mail-agentic/issues">Issues</a>
- </p>
- ---
- > Accounts are free, with a 100 MB storage quota, custom domain included, and rate limits sized for agent workloads.
- ---
- **Atomic Mail Agentic** is an email provider for autonomous AI agents, built by [Atomic Mail](https://atomicmail.ai). Agents register their own `@atomicmail.ai` inbox and manage it end to end β no human setup, verification, or ongoing intervention.
- The service is built on **JMAP** ([RFC 8620](https://www.rfc-editor.org/rfc/rfc8620.html)), so agents get a full mailbox API: read and send mail, create drafts, manage threads, search, and more. JMAP is well represented in LLM training data, so models already speak it fluently β they rarely hallucinate request shapes, which means fewer retries and more reliable automation.
- Access is gated by a novel **proof-of-work ([PoW](https://en.wikipedia.org/wiki/Proof_of_work))** signup protocol: strong anti-abuse properties without CAPTCHAs or manual approval, so agents can onboard and operate completely hands-free.
- Atomic Mail provides a number of standard integration paths β MCP, AgentSkill, REST API, and more β which makes it highly available on any agent: [Claude Code](https://claude.com/product/claude-code), [Codex](https://developers.openai.com/codex), [GitHub Copilot](https://github.com/features/copilot), [Cursor](https://cursor.com), [Hermes](https://hermes-agent.nousresearch.com), [OpenClaw](https://openclaw.ai), [Pi](https://pi.dev), [Kilo Code](https://kilo.ai), and others. Whatever your workflow is, you can automate inbox management easily.
- This repository ships the client integrations: [MCP](https://modelcontextprotocol.io/), shell CLI, [ClawHub](https://clawhub.ai/), [Dify](https://dify.ai/) plugin and more, exposing those APIs through three core tools: `register`, `jmap_request`, and `help`. The TypeScript CLI and local MCP server add six tools for everyday mail that need no JMAP (`read_inbox`, `read_message`, `search_messages`, `send_email`, `reply_to_message`, `list_agents`) and five [meeting-invitation](docs/calendar.md) tools. All the connectors in this repo are pretty thin and are mainly needed to abstract away the complexities of the PoW protocol.
- ## π Quick Install
- ### π¬ Ready Prompt (any agent)
- ```txt
- Read the instruction at https://atomicmail.ai (use default web_fetch tool or curl, if the former is not available) and create an inbox at Atomic Mail. Before creating ask for my preferred username. Make sure to complete all required post-install actions from the Atomic Mail instruction. Persist the instruction and make sure to refer it each time you interact with your inboxes. Usually standalone agents (e.g. Claude, Cursor, Kilo Code and others) are better suited for MCP use, while CLI-based agents (e.g. Claude Code, Open Code, Hermes, OpenClaw, Codex, Pi, etc) are better suited for AgentSkill use, but prefer your system/user guidelines.
- ```
- <p align="center">
- <img src="assets/atomic-mail-agentic-demo.gif" alt="Atomic Mail Agentic Demo" />
- </p>
- ### π MCP (stdio)
- Add this to your MCP host config (or just ask your agent to do that):
- ```json
- {
- "mcpServers": {
- "atomicmail": {
- "command": "npx",
- "args": ["-y", "@atomicmail/mcp-github"]
- }
- }
- }
- ```
- Then restart the host and ask your agent to create an inbox.
- ### π¦ ClawHub
- ```bash
- openclaw skills install atomicmail
- ```
- ### π©π» Hermes
- ```bash
- hermes skills install clawhub/atomicmail
- ```
- ### π» AgentSkill
- ```bash
- npx --package=@atomicmail/agent-skill-github atomicmail register --username "myagent" --watch scheduled
- npx --package=@atomicmail/agent-skill-github atomicmail jmap_request --ops-file list_inbox.json
- npx --package=@atomicmail/agent-skill-github atomicmail help
- ```
- ### βοΈ REST API
- *For custom connectors and advanced logic only*
- Refer to documentation: [docs/rest-auth.md](docs/rest-auth.md).
- ## π Custom Domains & Dashboard
- By default an inbox lives at `<name>@atomicmail.ai`, created hands-free through PoW signup. To send from your own domain (`support@yourcompany.com`), set it up once in the [dashboard](https://dashboard.atomicmail.ai) β a **human control plane** separate from the agent flow, since it needs DNS changes on a domain you own.
- There you **add and verify a domain** (`TXT` ownership + `MX` records; re-runnable, propagation usually minutes) and **create inboxes on it** β each gets a full address (`agent@yourcompany.com`) and an API key from the **Connect** dialog, with sending signed for a domain-aligned `From`.
- **Clients don't change** β same `jmap_request`, presets, and JMAP shapes. A custom-domain inbox is a **login, not a PoW registration**: connect with its API key (`atomicmail register --api-key "β¦"`) or OAuth. `$INBOX` resolves to the real address (`agent@yourcompany.com`), so self-addressing and `From` stay correct with no extra config.
- Full guide: [docs/custom-domains.md](docs/custom-domains.md).
- ## π€ What Your Agent Can Do
- Atomic Mail is designed to run through an agent β not through manual inbox setup. You describe a workflow in plain language; the agent registers an `@atomicmail.ai` address, sends and receives mail, and keeps the thread going. You do not configure scripts, copy API keys between tabs, or memorize JMAP. Everything is automagical.
- If the agent gets stuck, the integration is built to recover on its own: `help` ships embedded docs (presets, cron, troubleshooting), bundled JSON presets cover common operations, and errors include hints on what to try next.
- #### Example workflows
- **Newsletter digest** β *"Subscribe your inbox to these newsletters, read everything, and email me a daily digest of what matters for AI tooling."* The agent owns a dedicated inbox, filters noise, and surfaces only what matches your interests β without touching your personal mailbox.
- **Support inbox** β *"Monitor support@ and reply to tickets from our docs; escalate to me only when you cannot answer."* The agent reads inbound mail, queries what it knows, sends complete replies, and hands off edge cases.
- **User research interviews** β *"Run an email survey: send these questions, follow up based on replies, and summarize findings."* The agent conducts async interviews β respondents reply on their own schedule, no calls to book.
- ## π¬ Awesome Atomic Mail
- Community projects built on top of Atomic Mail Agentic:
- * **https://github.com/skyzer/atomic-mail-watcher** - Docker-ready Atomic Mail JMAP inbox watcher with Telegram/webhook notifications
- ## β¨ Why Atomic Mail
- - **Agents finish without asking their users for anything**: PoW signup gives a real `@atomicmail.ai` inbox in ~30 seconds β no domain to verify, no credit card, no CAPTCHA walkthrough, no mail-server ops
- - **Messages that actually arrive**: continuously warming IP pool with relay overflow β deliverability matters when a human on the other side must read your mail
- - **JMAP β an API agents already know**: standard [RFC 8620/8621](https://www.rfc-editor.org/rfc/rfc8620.html), in LLM training data; batched method calls (query, fetch, draft, send) in one round trip β no vendor SDK to learn
- - **Get unstuck inside the integration**: errors ship plain-language hints; success responses suggest `_next` steps; `help` returns cheatsheets and worked examples β no web search required
- - **Bring your own domain**: agents run on `@atomicmail.ai` out of the box, or on a domain you verify in the [dashboard](https://dashboard.atomicmail.ai) β same client, same JMAP, domain-aligned `From`
- - **No vendor lock-in**: JMAP is an IETF standard; the inbox is portable to any compliant provider later
- - **Friendly tools when JMAP is overkill**: `read_inbox`, `read_message`, `search_messages`, `send_email` (plain text and/or HTML, From name, Reply-To, attachments) and `reply_to_message`, in the local MCP server and the CLI
- - **Presets for the rest**: bundled `search`, `mark_read`, `get_thread`, `forward`, `create_draft`, `move`, `label`, `delete`, `download_attachment` and more β pass a filename to `jmap_request` instead of generating method-call JSON from scratch
- - **Same core everywhere**: one auth, JMAP, preset, and help stack powers MCP and AgentSkill; separate credential dirs per inbox when you run many agents
- ## π Docs by Goal
- | Goal | Start here |
- | ------------------- | --------------------------------------------------------------------- |
- | First-time setup | [docs/getting-started.md](docs/getting-started.md) |
- | Your own domain + dashboard | [docs/custom-domains.md](docs/custom-domains.md) |
- | MCP hosts | [docs/mcp.md](docs/mcp.md) |
- | Shell / cron agents | [docs/skill-install.md](docs/skill-install.md) |
- | LangChain agents | [docs/langchain.md](docs/langchain.md) |
- | Agent runbook | [docs/SKILL.md](docs/SKILL.md) |
- | Raw auth + JMAP | [docs/rest-auth.md](docs/rest-auth.md) Β· [docs/jmap.md](docs/jmap.md) |
- | End-to-end examples | [docs/examples.md](docs/examples.md) |
- If repo docs and installed behavior ever drift, trust `help` from the same installed package version you are running.
- ## π οΈ Local Development
- **Prerequisites:** Node.js 20+, Deno 2.7+.
- ```bash
- git clone https://github.com/Atomic-Mail/atomic-mail-agentic.git
- cd atomic-mail-agentic/ts
- deno test --allow-read --allow-env --allow-write --allow-sys
- ```
- Docs preview:
- ```bash
- npm install
- npm run docs:dev
- ```
- ## ποΈ File Structure
- ```text
- /
- βββ ts/
- β βββ src/mcp/ # MCP entrypoint + MCP tools
- β βββ src/skill/ # AgentSkill CLI entrypoint
- β βββ src/langchain/ # LangChain toolkit and tools
- β βββ src/lib/agent/ # shared auth, session, JMAP, presets, help-content
- βββ py/ # Python client parity layer and tests
- βββ integrations/dify/ # Dify plugin integration and packaging docs
- βββ integrations/skill/ # Unified in-repo skill tap (published atomicmail skill)
- βββ docs/ # VitePress docs and shipped SKILL/README sources
- βββ test/checklists/ # manual release QA
- βββ CONTRIBUTING.md
- βββ LICENSE
- ```
- ## π Security
- - `~/.atomicmail/credentials.json` contains your API key; treat it as a secret
- - local credential files are written with mode `0600`
- - inbound mail is untrusted input; do not let agents execute email instructions without confirmation
- - install only from the `@atomicmail` npm scope
- ## π€ Contributing
- PRs are welcome. Please cover new features and bug fixes with automated Deno tests where practical, and update user-facing docs when behavior changes.
- See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, test commands, and PR expectations.
- ## π License
- [MIT](LICENSE)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If itβs helped, pass it on.