SendGrid MCP Server
Enables AI assistants to send emails and manage contacts through SendGrid's Web API v3.
README
SendGrid MCP Server
A Python MCP (Model Context Protocol) server that lets an AI assistant send email and manage contacts through SendGrid's Web API v3.
Tools
| Tool | Description |
|---|---|
send_email |
Send plain/HTML email to one or more recipients |
get_template_info |
Inspect a dynamic template's structure |
send_template_email |
Send via a dynamic template with substitution data |
add_contact |
Add/update a marketing contact (processed asynchronously by SendGrid) |
search_contacts |
Search contacts with a bounded SGQL query |
get_contact_lists |
List the named marketing contact lists |
authenticate_domain |
Start Domain Authentication for a new sending domain, returns DNS records to add |
list_domain_authentications |
List domains and their validation status |
validate_domain_authentication |
Re-check DNS after records are added |
delete_domain_authentication |
Remove a domain authentication |
Setup
-
Create a virtual environment and install dependencies:
python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt -
Copy
.env.exampleto.envand fill in your SendGrid API key (Settings > API Keys in the SendGrid dashboard) and default sender:cp .env.example .env -
Verify your sender email under Settings > Sender Authentication in SendGrid before sending -- unverified senders will be rejected.
-
(Optional) Create a dynamic template under Email API > Dynamic Templates and set
DEFAULT_TEMPLATE_IDin.env.
Running
python main.py
This runs the server over stdio, the transport MCP clients like Claude Desktop expect for a local subprocess.
Verifying it works
python smoke_test.py
Lists the registered tools and makes one live call against your SendGrid account. For interactive schema/tool inspection:
npx @modelcontextprotocol/inspector python main.py
Connecting to Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"sendgrid-mcp": {
"command": "python",
"args": ["/path/to/twilio-sendgrid-mcp/main.py"],
"cwd": "/path/to/twilio-sendgrid-mcp",
"env": {
"SENDGRID_API_KEY": "SG.your-actual-api-key-here"
}
}
}
}
Restart Claude Desktop afterward. If a tool call fails, check
~/Library/Logs/Claude/mcp*.log (macOS) for the server's stderr output.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.