GMAIL -Agent
MCP Agent for Gmail outreach and lead nurturing.
claude mcp add --transport stdio brandononchain-gmail-mcp-agent uvx gmail-mcp-agent \ --env RESUME="false" \ --env LOG_FILE="send_log.csv" \ --env LOG_LEVEL="INFO" \ --env PER_MINUTE="12" \ --env TOKEN_FILE="token.json" \ --env MCP_SERVER_PORT="8000" \ --env CREDENTIALS_FILE="credentials.json"
How to use
This MCP server provides a 24/7 Gmail outreach and lead-nurturing system. It orchestrates automated email campaigns, follow-up sequences at 3 and 7 days, response tracking, and lead scoring, all controllable via the MCP client. The server runs Python components that manage Gmail API interactions, lead nurturing logic, and a lightweight dashboard for monitoring. You can start, stop, query status, generate reports, and run test emails through the MCP client as well as execute individual scripts for nurturing, dashboard viewing, and CSV-based email sending. When combined with Docker deployment, the system becomes a production-ready, scalable automation platform for enterprise lead management.
How to install
{"Prerequisites:","- Python 3.9+ and pip installed on your system","- Git installed","- Optional: Docker and docker-compose for containerized deployment","","1) Clone the repository","git clone https://github.com/brandononchain/GMAIL-MCP-Agent.git","cd GMAIL-MCP-Agent","","2) Install Python dependencies","pip install -r requirements.txt","","3) Configure Gmail API credentials","- Obtain OAuth2 credentials from Google Cloud Console","- Save the credentials JSON as credentials.json in the project root","- Update sender email and nurturing settings in nurturing_config.json","","4) Run the MCP server (via UV SDK as configured)","- If using UVX (Python/uv):","uvx gmail-mcp-agent","Note: The exact command may vary based on your packaging; ensure the command matches the mcp_config entry used by your environment.","","5) Optional Docker deployment","- Build and start containers using Docker Compose","./deploy.sh # One-click deployment (recommended)","docker-compose up -d # Manual deployment"}
Additional notes
Tips and considerations:
- Ensure the Gmail API credentials (credentials.json) and OAuth tokens (token.json) are securely stored and not committed to version control.
- The MCP server port defaults to 8000; adjust MCP_SERVER_PORT in the environment if you run multiple MCP servers.
- The nurturing configuration (nurturing_config.json) controls sender_email, follow-up days (3 and 7), and automation settings. Customize to fit your workflow.
- For production, use Docker deployment to leverage containerization, health checks, and restart policies.
- Logs are written to send_log.csv by default; rotate or archive periodically to prevent growth from filling disk space.
Related MCP Servers
mcpcat-python-sdk
MCPcat is an analytics platform for MCP server owners 🐱.
zerodha
Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)
symfony
A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.
mcp-framework
Rust MCP framework for building AI agents
unity
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.
ia-na-pratica
IA na Prática: LLM, RAG, MCP, Agents, Function Calling, Multimodal, TTS/STT e mais