MCP Email Server with SendGrid
An MCP server that enables AI applications to send text, HTML, and template-based emails using SendGrid. It supports file attachments, CC/BCC recipients, and easy deployment via Python or Docker.
README
✉️ MCP Email Server with SendGrid
A Model Context Protocol (MCP) server that provides email sending capabilities through SendGrid. This server enables AI applications like Claude Desktop, Langflow, and other MCP clients to send emails programmatically.
🚀 Features
- 📧 Basic Email Sending - Send text or HTML emails
- 🎨 Template Support - Use SendGrid dynamic templates
- 📎 File Attachments - Attach files to emails
- 👥 CC/BCC Support - Send copies to multiple recipients
- 🐳 Docker Ready - Containerized deployment
- 🔒 Secure - Environment-based configuration
📋 Prerequisites
- Python 3.10 or higher
- SendGrid account and API key (Sign up here)
- Verified sender email address in SendGrid
- Docker (optional, for containerized deployment)
🛠️ Installation
Option 1: Local Python Setup
-
Clone or navigate to the repository:
cd d:\repos\mcp_mail -
Create and activate virtual environment:
python -m venv venv .\venv\Scripts\activate # Windows -
Install dependencies:
pip install -e . -
Configure environment variables:
copy .env.example .envEdit
.envand add your credentials:SENDGRID_API_KEY=your_actual_sendgrid_api_key DEFAULT_FROM_EMAIL=your-verified-email@example.com DEFAULT_FROM_NAME=Your Name
Option 2: Docker Deployment
-
Configure environment:
copy .env.example .env # Edit .env with your credentials -
Build and run with Docker Compose:
docker-compose up -dOr build manually:
docker build -t mcp-email-server . docker run --env-file .env mcp-email-server
🔧 Configuration
SendGrid Setup
-
Create a SendGrid account at sendgrid.com
-
Generate an API key:
- Go to Settings → API Keys
- Click "Create API Key"
- Select "Full Access" or "Restricted Access" with Mail Send permissions
- Copy the API key (you'll only see it once!)
-
Verify sender email:
- Go to Settings → Sender Authentication
- Verify the email address you'll use as the sender
- This is required by SendGrid to prevent spam
Environment Variables
| Variable | Required | Description |
|---|---|---|
SENDGRID_API_KEY |
Yes | Your SendGrid API key |
DEFAULT_FROM_EMAIL |
Yes | Default sender email (must be verified in SendGrid) |
DEFAULT_FROM_NAME |
No | Default sender name displayed to recipients |
📖 Usage
Running the Server
Local:
python server.py
Docker:
docker-compose up
The server communicates via stdio (standard input/output) using the MCP protocol.
Available MCP Tools
1. send_email
Send a basic email with text or HTML content.
Parameters:
to_email(required): Recipient email addresssubject(required): Email subject linebody(required): Email content (text or HTML)from_email(optional): Sender email (uses DEFAULT_FROM_EMAIL if not provided)from_name(optional): Sender namecc_emails(optional): List of CC recipientsbcc_emails(optional): List of BCC recipientsis_html(optional): Set to true for HTML emails (default: false)
Example:
{
"to_email": "recipient@example.com",
"subject": "Hello from MCP",
"body": "<h1>Welcome!</h1><p>This is a test email.</p>",
"is_html": true
}
2. send_email_with_template
Send an email using a SendGrid dynamic template.
Parameters:
to_email(required): Recipient email addresstemplate_id(required): SendGrid template IDdynamic_data(required): Dictionary of template variablesfrom_email(optional): Sender emailfrom_name(optional): Sender namesubject(optional): Override template subject
Example:
{
"to_email": "user@example.com",
"template_id": "d-1234567890abcdef",
"dynamic_data": {
"username": "John",
"action_url": "https://example.com/verify"
}
}
3. send_email_with_attachments
Send an email with file attachments.
Parameters:
to_email(required): Recipient email addresssubject(required): Email subject linebody(required): Email contentattachment_paths(required): List of file paths to attachfrom_email(optional): Sender emailfrom_name(optional): Sender nameis_html(optional): HTML email flag
Example:
{
"to_email": "recipient@example.com",
"subject": "Report Attached",
"body": "Please find the report attached.",
"attachment_paths": ["/path/to/report.pdf", "/path/to/data.csv"]
}
🔌 Integration Examples
Claude Desktop
Add to your Claude Desktop config file (claude_desktop_config.json):
{
"mcpServers": {
"email": {
"command": "python",
"args": ["d:\\repos\\mcp_mail\\server.py"],
"env": {
"SENDGRID_API_KEY": "your_api_key",
"DEFAULT_FROM_EMAIL": "your-email@example.com",
"DEFAULT_FROM_NAME": "Your Name"
}
}
}
}
Or using Docker:
{
"mcpServers": {
"email": {
"command": "docker",
"args": ["run", "-i", "--rm", "--env-file", "d:\\repos\\mcp_mail\\.env", "mcp-email-server"]
}
}
}
Langflow Integration
- Install an MCP client component in Langflow (if available) or use a custom Python component
- Configure the MCP server connection with the email server's stdio transport
- Call the email tools from your Langflow flows
See examples/langflow_integration.md for detailed instructions.
Python Client Example
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
server_params = StdioServerParameters(
command="python",
args=["d:/repos/mcp_mail/server.py"],
env={
"SENDGRID_API_KEY": "your_key",
"DEFAULT_FROM_EMAIL": "your@email.com"
}
)
async with stdio_client(server_params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
# Call the send_email tool
result = await session.call_tool("send_email", {
"to_email": "recipient@example.com",
"subject": "Test Email",
"body": "Hello from MCP!",
"is_html": False
})
print(result)
🧪 Testing
Run the test script to verify functionality:
python test_server.py
This will test the email sending functions with mocked SendGrid responses.
🐛 Troubleshooting
"SendGrid client not initialized"
- Ensure
SENDGRID_API_KEYis set in your.envfile - Verify the API key is valid and has Mail Send permissions
"403 Forbidden" error
- Your sender email address must be verified in SendGrid
- Go to SendGrid Settings → Sender Authentication
"No from_email provided"
- Set
DEFAULT_FROM_EMAILin your.envfile, or - Provide
from_emailparameter in each request
Attachments not working
- Ensure the file paths are absolute and accessible
- Check file permissions
- Verify files exist at the specified paths
📚 Resources
📄 License
MIT License - feel free to use this in your projects!
🤝 Contributing
Contributions welcome! Feel free to submit issues or pull requests.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。