MCP.so
ログイン
A

Atomic Mail Agentic

@Atomic-Mail

リポジトリ

Atomic Mail Agentic について

Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.

#email#mail#gmail

基本情報

カテゴリ

推論

トランスポート

stdio

公開者

Atomic-Mail

投稿者

Alexander Vtyurin

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "atomicmail": {
      "command": "npx",
      "args": [
        "-y",
        "@atomicmail/mcp-mcpso"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Atomic Mail Agentic?

Atomic Mail Agentic is an email provider for autonomous AI agents, built by Atomic Mail. It gives agents their own @atomicmail.ai inbox without human setup, using JMAP (RFC 8620) and a proof-of-work signup protocol for hands-free, CAPTCHA-free onboarding.

How to use Atomic Mail Agentic?

Add the MCP server to your host config (npx -y @atomicmail/mcp-github) or use the AgentSkill CLI (npx @atomicmail/agent-skill-github). Then ask your agent to create an inbox; it registers, sends/receives mail, and manages threads via the register, jmap_request, and help tools.

Key features of Atomic Mail Agentic

  • Agents get a real @atomicmail.ai inbox autonomously
  • Full JMAP API: read, send, draft, thread, search
  • Proof-of-work signup: no CAPTCHA or manual approval
  • MCP, AgentSkill, ClawHub, Hermes, Dify integrations
  • Presets for common operations (send, list, reply)
  • Help tool with embedded docs and recovery hints

Use cases of Atomic Mail Agentic

  • Newsletter digest: agent subscribes, reads, and emails a daily summary
  • Support inbox: agent replies to tickets, escalates uncertain cases
  • User research interviews: agent sends survey, follows up, summarizes replies

FAQ from Atomic Mail Agentic

What is the difference between MCP and AgentSkill integrations?

MCP is for GUI-based agents (e.g., Claude, Cursor); AgentSkill is for CLI-based agents (e.g., Claude Code, Hermes). Both expose the same email tools and backend.

What is the open alpha status?

Accounts are free with a 100 MB storage quota and strict rate limits. Public stable release is coming soon.

How does signup work for an agent?

Agents use a proof-of-work protocol to register without human verification, credit cards, or CAPTCHAs, getting an @atomicmail.ai inbox in about 30 seconds.

Where are credentials stored?

Credentials are written to ~/.atomicmail/credentials.json with file mode 0600. Treat this API key as a secret.

What transport/auth is used?

The MCP server uses stdio transport. Underlying JMAP requests are authenticated via API keys obtained during the proof-of-work registration.

コメント

「推論」の他のコンテンツ

Agentic MCP Client

peakmojo

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

41

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

27

End-to-End Agentic AI Automation Lab

MDalamin5

This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.

83

ArduPilot MCP Server Sandbox

hfujikawa77

ArduPilotドローンをAIエージェントから操作するMCPサーバーです。

9

Deno Sandbox MCP Server

bewt85

An MCP server that allows you to run TypeScript, JavaScript, and Python code in a sandbox on your local machine using the Deno® sandbox. This server provides a controlled environment for executing code with explicit permission controls.

13