by egyptianego17
Email MCP Server is a simple Model Context Protocol (MCP) server that enables AI agents to send emails and attach files through SMTP, acting as a bridge for AI assistants to interact with email services.
Email MCP Server is a simple Model Context Protocol (MCP) server that enables your AI agent to send emails and attach files through SMTP. It acts as a bridge, allowing AI assistants to interact with email services.
To use Email MCP Server, follow these steps:
uv (Python package manager) by running curl -LsSf https://astral.sh/uv/install.sh | sh and then source ~/.bashrc.email-mcp-server directory and run uv sync.uv run python test_email.py or run the server directly with uv run main.py.SMTP_HOST, SMTP_PORT, SMTP_SECURE, SMTP_USER, SMTP_FROM, SMTP_PASS).test_smtp_connection_tool to verify email setup.send_email for simple sending and send_custom_email for advanced features.Q: What if I encounter "Missing Configuration"? A: Ensure all environment variables are set in the Claude Desktop config, verify the directory path is correct and absolute, and restart Claude Desktop after making changes.
Q: What if "Authentication Failed"? A: For Gmail/Yahoo, use app passwords instead of regular passwords. Enable 2-Factor Authentication first, then generate an app password. Double-check your username and password.
Q: What if there are "Connection Issues"? A: Verify that the SMTP host and port are correct. Check your internet connection. Be aware that some networks might block SMTP ports.
Q: What if "Server Not Found"?
A: Make sure uv is installed and in your PATH. Check that the directory path exists and verify that the project dependencies are installed with uv sync.
This MCP (Model Context Protocol) server lets your AI assistant send emails for you.
Your AI assistant can:
send_email - Simple Email SendingSend emails quickly using your environment configuration:
send_custom_email - Advanced Email FeaturesSend emails with full control:
test_smtp_connection_tool - Check SetupTest your email settings before sending important emails.
# Install uv (Python package manager)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Restart your terminal or run:
source ~/.bashrc
cd email-mcp-server
uv sync
# Test your email setup
uv run python test_email.py
# Run the server directly (for testing)
uv run main.py
Add this to your Claude Desktop configuration or Cursor file:
{
"mcpServers": {
"mcp-server": {
"command": "uv",
"args": [
"--directory",
"path/to/the/app/email-mcp-server",
"run",
"main.py"
],
"env": {
"SMTP_HOST": "",
"SMTP_PORT": "",
"SMTP_SECURE": "",
"SMTP_USER": "",
"SMTP_FROM": "",
"SMTP_PASS": ""
}
}
}
}
Important: Change the directory path to match your actual installation location.
Send a basic email:
"Send an email to john@company.com saying the meeting is tomorrow at 2 PM"
Send with HTML formatting:
"Send an HTML email to team@company.com with subject 'Weekly Update' and create a nice formatted message about this week's progress"
Test your setup:
"Test the email connection to make sure it's working"
Send to multiple people with attachments:
"Send a custom email to the team about the project update. Send to team@company.com, CC manager@company.com, and attach the project report"
"env": {
"SMTP_HOST": "smtp.gmail.com",
"SMTP_PORT": "587",
"SMTP_SECURE": "false",
"SMTP_USER": "your-email@gmail.com",
"SMTP_FROM": "your-email@gmail.com",
"SMTP_PASS": "your-app-password"
}
Gmail Setup Steps:
"env": {
"SMTP_HOST": "smtp-mail.outlook.com",
"SMTP_PORT": "587",
"SMTP_SECURE": "false",
"SMTP_USER": "your-email@outlook.com",
"SMTP_FROM": "your-email@outlook.com",
"SMTP_PASS": "your-password"
}
Replace the SMTP settings with your provider's details. Most providers use:
| Variable | Description | Example |
|---|---|---|
SMTP_HOST |
Your email server | smtp.gmail.com |
SMTP_PORT |
Server port | 587 |
SMTP_SECURE |
Use SSL (true/false) | false |
SMTP_USER |
Your username | user@gmail.com |
SMTP_FROM |
Sender address | noreply@company.com |
SMTP_PASS |
Your password | your-password |
uv is installed and in your PATHuv sync# Test configuration and connection
uv run python test_email.py
# Send a real test email to yourself
uv run python test_email.py --send-real
MIT License - Feel free to use and modify as needed.
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by danny-avila
Provides a customizable ChatGPT‑like web UI that integrates dozens of AI models, agents, code execution, image generation, web search, speech capabilities, and secure multi‑user authentication, all open‑source and ready for self‑hosting.
by ahujasid
BlenderMCP integrates Blender with Claude AI via the Model Context Protocol (MCP), enabling AI-driven 3D scene creation, modeling, and manipulation. This project allows users to control Blender directly through natural language prompts, streamlining the 3D design workflow.
by pydantic
Enables building production‑grade generative AI applications using Pydantic validation, offering a FastAPI‑like developer experience.
by GLips
Figma-Context-MCP is a Model Context Protocol (MCP) server that provides Figma layout information to AI coding agents. It bridges design and development by enabling AI tools to directly access and interpret Figma design data for more accurate and efficient code generation.
by mcp-use
Easily create and interact with MCP servers using custom agents, supporting any LLM with tool calling and offering multi‑server, sandboxed, and streaming capabilities.
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
by lharries
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp that allows users to search, read, and send WhatsApp messages (including media) through AI models like Claude. It connects directly to your personal WhatsApp account via the WhatsApp web multi-device API and stores messages locally in a SQLite database.
by idosal
GitMCP is a free, open-source remote Model Context Protocol (MCP) server that transforms any GitHub project into a documentation hub, enabling AI tools to access up-to-date documentation and code directly from the source to eliminate "code hallucinations."
by Klavis-AI
Klavis AI provides open-source Multi-platform Control Protocol (MCP) integrations and a hosted API for AI applications. It simplifies connecting AI to various third-party services by managing secure MCP servers and authentication.