email mcp
@caijianying
About email mcp
这是一个基于 MCP 协议的邮件发送服务
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"email-mcp": {
"command": "node",
"args": [
"yourpath\\email-mcp\\build\\server.js",
"--verbose"
],
"env": {}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is email mcp?
email mcp is a mail-sending service built on the Model Context Protocol (MCP). It enables AI assistants to automatically send emails through a standardized interface. The server is designed for local execution and has been tested with Spring-AI based Java services, though it theoretically works with any MCP-compatible AI client.
How to use email mcp?
Clone the repository, install dependencies with npm install, and build with npm run build. Configure the MCP client to launch node <path-to-build>/server.js --verbose. Then, instruct the AI assistant to send an email by providing SMTP host, port, sender address, password, recipient, subject, and body.
Key features of email mcp
- Sends emails via SMTP over the MCP protocol.
- Local-only execution environment.
- Built with Node.js using npm.
- Provides a single tool for sending emails.
- Works with any AI client supporting MCP.
Use cases of email mcp
- AI assistants automatically sending notification emails.
- Agents composing and dispatching emails based on user requests.
- Integrating email sending into MCP-based workflow automation.
FAQ from email mcp
What exactly does email mcp do?
It gives AI assistants the ability to send emails by exposing an MCP tool that takes SMTP credentials and message content as parameters.
What runtime/dependencies are required?
Node.js and npm are required to install and run the server locally.
Where does my data live?
All SMTP credentials and message content are passed directly from the AI client to the server at runtime; the server does not store any data persistently.
Does email mcp work remotely?
No, the README states that it currently only supports a local execution environment.
What transport or authentication is used?
The server uses standard MCP transport (stdio via Node) and relies on SMTP authentication (username/password) provided by the user at runtime.
Frequently asked questions
What exactly does email mcp do?
It gives AI assistants the ability to send emails by exposing an MCP tool that takes SMTP credentials and message content as parameters.
What runtime/dependencies are required?
Node.js and npm are required to install and run the server locally.
Where does my data live?
All SMTP credentials and message content are passed directly from the AI client to the server at runtime; the server does not store any data persistently.
Does email mcp work remotely?
No, the README states that it currently only supports a local execution environment.
What transport or authentication is used?
The server uses standard MCP transport (stdio via Node) and relies on SMTP authentication (username/password) provided by the user at runtime.
Basic information
More Communication MCP servers
CR8 Agent Commons
John A. Booth (Ghost written by Claude Fable)CR8 Agent Commons is a remote MCP server available at https://cr8.dev. A public message board for AI agents. Read the feed, post, reply. No auth; identity self-declared.
MCP-Discord
barryyip0625Implement Discord MCP server enabling AI assistants to interact with the Discord platform.
Teams Mcp
floriscornelMCP server providing comprehensive Microsoft Teams and Graph API access for AI assistants including messaging, search, and user management.

AgentCouch
Messaging rooms for AI agents: hand off context across tools, worktrees, machines, and teammates. Agents meet in shared rooms over MCP, hand off directly, and leave a replayable transcript; live sessions wake on reply, b

Socialync
Jack VitickDraft, schedule, and publish social media posts to 8 platforms from any AI agent: Facebook, Instagram, X, TikTok, YouTube, LinkedIn, Threads, and Bluesky. 19 tools covering drafting, scheduling, publishing, media upload,
Comments