SendGrid MCP Server
Enables AI models to send emails, manage contacts, and interact with SendGrid's email platform via MCP.
README
SendGrid MCP Server
A production-ready Model Context Protocol (MCP) Server for SendGrid email services, built with FastMCP 2.0. This server enables AI models like Claude, GPT, and others to send emails, manage contacts, and interact with SendGrid's powerful email platform.
🚀 Features
- 📧 Email Management: Send HTML/text emails with templates and attachments
- 👥 Contact Management: Add contacts and manage mailing lists
- 🔐 Secure Authentication: Bearer token authentication with fallback support
- ⚡ Rate Limiting: Built-in API rate limiting to prevent abuse
- 🛡️ Production Ready: Comprehensive error handling and logging
- 🔧 Easy Configuration: Environment-based configuration management
📋 Requirements
- Python 3.8+
- SendGrid API Key
- FastMCP 2.0
🛠️ Installation
-
Clone the repository:
git clone https://github.com/FINCH285/SendGrid-MCP-Server.git cd SendGrid-MCP-Server -
Install dependencies:
pip install -r requirements.txt -
Set up environment variables:
cp .env.example .envEdit
.envwith your SendGrid configuration:SENDGRID_API_KEY=your_sendgrid_api_key_here DEFAULT_FROM_EMAIL=your-verified-email@example.com DEFAULT_FROM_NAME=Your Name DEFAULT_TEMPLATE_ID=your-template-id RATE_LIMIT=10 DEBUG=false
🚀 Usage
Running the Server
python main.py
The server will start and listen for MCP connections via STDIO.
Available Tools
Email Tools
send_email- Send HTML/text emails to multiple recipientsget_template_info- Fetch SendGrid template detailssend_template_email- Send emails using dynamic templates
Contact Tools
add_contact- Add/update contacts with custom fieldsget_contact_lists- Retrieve all contact lists
🔧 Configuration
Authentication
The server supports two authentication methods:
- Environment Variable: Set
SENDGRID_API_KEYin your.envfile - Bearer Token: Pass API key via Authorization header in MCP requests
📚 SendGrid Configuration example
{
"mcpServers": {
"sendgrid-mcp": {
"command": "python",
"args": ["/path/to/your/project/main.py"],
"cwd": "/path/to/your/project",
"disabled": false,
"env": {
"SENDGRID_API_KEY": "SG.your-actual-api-key-here"
}
}
}
}
For Windows users, use paths like:
"args": ["C:\\Users\\YourUsername\\project-folder\\main.py"]
"cwd": "C:\\Users\\YourUsername\\project-folder"
For macOS/Linux users, use paths like:
"args": ["/Users/yourusername/project-folder/main.py"]
"cwd": "/Users/yourusername/project-folder"
Key configuration elements:
-
"sendgrid-mcp": The server name/identifier (customizable)
-
args: Specifies the path to your main.py file
-
cwd: Sets the working directory to your project folder
-
disabled: Set to false to enable the server
-
env: Contains your SendGrid API key (replace with your actual key starting with "SG.")
🏗️ Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ AI Model │◄──►│ FastMCP │◄──►│ SendGrid │
│ (Claude/GPT) │ │ Server │ │ API │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│ │ │
│ MCP Protocol │ HTTP/REST │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Tools Layer │ │ Auth Layer │ │ Config Layer │
│ • email_tools │ │ • Bearer Token │ │ • Environment │
│ • contact_tools │ │ • API Key Auth │ │ • Rate Limits │
└─────────────────┘ └─────────────────┘ └─────────────────┘
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Support
- Issues: GitHub Issues
- SendGrid Documentation: SendGrid API Docs
- FastMCP Documentation: FastMCP Docs
🙏 Acknowledgments
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。