- Home
- MCP servers
- Gemini Email Subject Generator
Gemini Email Subject Generator
- typescript
2
GitHub Stars
typescript
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"falahgs-gemini-email-subject-generator-mcp": {
"command": "node",
"args": [
"path/to/gemini-email-subject-generator/dist/index.js"
],
"env": {
"GEMINI_API_KEY": "your_api_key_here",
"NODEMAILER_EMAIL": "your.email@gmail.com",
"NODEMAILER_PASSWORD": "your_app_password_here"
}
}
}
}You can deploy and run a Gemini-powered MCP server that generates engaging email subjects and detailed thinking outputs. It exposes a stdio-based local server command you run to start the integration, and it includes secure handling of API keys and SMTP credentials for email delivery. This server is designed to work with an MCP client to automate AI-assisted email subject creation and structured thinking content.
How to use
Run the local MCP server from your development environment and connect your MCP client to it. You can send prompts to generate email subjects and, separately, requests to produce detailed thinking content. Use the email tool to compose messages with either HTML or plain text content, optionally attaching images that can render inline. Use the thinking tool to produce in-depth reasoning and planning text, then save or export the results for later use.
With the email tool, you provide a recipient, a subject prompt that asks for a catchy subject line, and the email body in text and/or HTML. The Gemini model will generate a subject, and the email is delivered using your configured SMTP account. Attachments can be included as data URIs and shown inline if supported by the client.
With the thinking tool, you supply a complex analysis prompt and optionally an output directory. The tool returns a detailed thinking narrative that you can review, refine, or save for reference during brainstorming and content creation.
How to install
Prerequisites are the following: node.js v16 or higher, TypeScript, Claude Desktop, a Google Gemini API key, and an SMTP email account for sending emails.
Step by step commands to set up the server locally:
# Clone the project repository
git clone [your-repo-url]
cd gemini-email-subject-generator
# Install dependencies
npm install
# Build the project
npm run build
Create a local environment file with credentials and keys used by the server:
GEMINI_API_KEY=your_api_key_here
NODEMAILER_EMAIL=your.email@gmail.com
NODEMAILER_PASSWORD=your_app_password_here
Claude Desktop configuration
Configure Claude Desktop to launch the MCP server with the required environment variables.
{
"mcpServers": {
"Gemini Email Generator": {
"command": "node",
"args": ["path/to/gemini-email-subject-generator/dist/index.js"],
"cwd": "path/to/gemini-email-subject-generator",
"env": {
"GEMINI_API_KEY": "your_api_key_here",
"NODEMAILER_EMAIL": "your.email@gmail.com",
"NODEMAILER_PASSWORD": "your_app_password_here"
}
}
}
}
Starting and testing the server
After the build, start the MCP server using the command shown in Claude Desktop configuration. Verify that the server starts without errors, then connect your MCP client and test sending an email with an AI-generated subject and optional HTML content.
Usage notes and examples
Email tool usage example shows how to request an AI-generated subject and provide both plain text and HTML content for the email. The tool will generate a subject based on your prompt and send the message using your configured SMTP account.
Available tools
send-email
Sends emails with AI-generated subjects using Gemini Flash 2, supporting HTML and plain text content, image attachments, secure authentication, error handling, and message tracking.
generate-thinking
Generates detailed thinking process text using Gemini's Flash 2 model, supports complex reasoning, and saves responses with timestamps to a configurable output directory.