mcp-mail-server and mcp-server-email

mcp-mail-server
64
Established
mcp-server-email
39
Emerging
Maintenance 13/25
Adoption 15/25
Maturity 18/25
Community 18/25
Maintenance 2/25
Adoption 9/25
Maturity 9/25
Community 19/25
Stars: 22
Forks: 12
Downloads: 8,235
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 71
Forks: 18
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
Stale 6m No Package No Dependents

About mcp-mail-server

yunfeizhu/mcp-mail-server

A lightweight Model Context Protocol (MCP) server that provides IMAP and SMTP email functionality for AI assistants like Claude in Cursor IDE. Built with TypeScript and optimized for easy deployment via npm/npx.

Supports multi-mailbox navigation with RFC 6154 auto-detection of special folders (Sent, Drafts), concurrent connection management with timeout guards, and comprehensive search operations (by sender/subject/date/keyword) with optional inbox-only filtering. Implements stateless message retrieval using UIDs rather than connection state, HTML-escape injection prevention in replies, and automatic attachment metadata extraction. Integrates with Claude Desktop, Cursor, Claude Code, and other MCP clients via stdio transport with environment-based configuration for TLS/SSL email servers.

About mcp-server-email

Shy2593666979/mcp-server-email

一个基于 MCP (Model Context Protocol) 的邮件服务,支持 LLM 发送带附件的电子邮件及在指定目录中搜索文件。提供安全的 SMTP 传输、多收件人支持和附件模式匹配搜索功能,适用于 Gmail、Outlook、Yahoo、QQ 邮箱和网易 126 邮箱等主流邮箱服务。

Implements MCP tools via stdio transport that LLMs invoke to compose emails with configurable SMTP backends—automatically routing messages through the correct server (Gmail, Outlook, Yahoo, etc.) based on sender domain. The `search_attachments` tool enables filesystem pattern matching for attachment discovery, while a whitelist restricts supported file types (documents, archives, images, text) for security. Integrates directly with Claude.app and other MCP clients through environment-based credential injection, supporting multi-recipient delivery with optional attachments.

Scores updated daily from GitHub, PyPI, and npm data. How scores work