MCP Email Service
Enables multi-account email management with AI-powered monitoring, intelligent filtering, and automated notifications across multiple platforms including Gmail, Outlook, QQ Mail, and 163 Mail.
README
Mailbox CLI
CLI-first email management for multi-account IMAP/SMTP with a local sync cache.
Primary interface: the mailbox CLI (Node.js implementation). This repo ships
prebuilt platform binaries via npm (no Python required for end users).
Supported Providers
- 163 Mail (mail.163.com / mail.126.com)
- QQ Mail (mail.qq.com)
- Gmail (mail.google.com)
- Outlook/Hotmail
- Custom IMAP servers
Install
npm (recommended)
npm install -g @leeguoo/mailbox-cli
mailbox --help
The npm package ships prebuilt binaries per platform (no Python required).
From source (development)
pnpm install
pnpm test
# build a local platform binary into mailbox-cli/packages/<platform>/bin/mailbox
pnpm build:binary
Configure accounts
mkdir -p ~/.config/mailbox
cp examples/accounts.example.json ~/.config/mailbox/auth.json
Config locations:
- Credentials:
~/.config/mailbox/auth.json - Other settings:
~/.config/mailbox/config.toml
Common commands
# CLI help
mailbox --help
# list accounts
mailbox account list --json
# list unread emails (cache by default)
mailbox email list --unread-only --limit 20 --json
# show one email
mailbox email show 123456 --account-id my_account_id --json
# mark read (use --dry-run to validate first)
mailbox email mark 123456 --read --account-id my_account_id --folder INBOX --dry-run --json
mailbox email mark 123456 --read --account-id my_account_id --folder INBOX --confirm --json
# delete
mailbox email delete 123456 --account-id my_account_id --folder INBOX --confirm --json
Cache + sync
- Cache DB default:
~/.local/share/mailbox/email_sync.db - Listing uses cache by default where possible. Add
--liveto force IMAP.
mailbox sync status --json
mailbox sync force --json
mailbox sync init
mailbox sync daemon
AI usage guide
If you're integrating this CLI into an AI agent, start here:
docs/AI_SKILL_MAILBOX_CLI.md
OpenClaw integration
This repo includes an OpenClaw skill at skills/mailbox/SKILL.md.
OpenClaw loads skills from:
<workspace>/skills~/.openclaw/skills
Quick link helper (symlink into ~/.openclaw/skills):
./scripts/link_openclaw_skill.sh
Force replace an existing link:
./scripts/link_openclaw_skill.sh --force
To use this repo without copying files, add the repo skills directory to
skills.load.extraDirs in ~/.openclaw/openclaw.json:
{
"skills": {
"load": {
"extraDirs": [
"/path/to/mcp-email-service/skills"
]
}
}
}
OpenClaw handles channel delivery and scheduling; mailbox returns structured JSON outputs and optional text summaries.
Verify OpenClaw picked up the skill:
openclaw skills list --eligible
openclaw skills check
Contract
docs/CLI_JSON_CONTRACT.md
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.