Druling MCP Server
Provides tools for interacting with Gmail, enabling AI agents to manage emails, send messages, and perform mailbox operations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Druling MCP Server
Install all dependencies
Run
pip install -r requirements-dev.txt
Related MCP server: Artificial Virtual Assistant (AVA)
How to run app using Docker with PostgreSQL
Install Docker Desktop
Run
docker compose up --buildRun
docker compose downto stop all services
How to run locally without postgres or docker
In database/core.py change the DATABASE_URL to sqlite
Run
make run
How to run tests
Run
pytestto run all tests
How to Add a New MCP Server
MCP (Model Context Protocol) servers provide tools and prompts for AI integrations. Follow these steps to add a new MCP server:
Step 1: Create the MCP Server Directory
Create a new directory under src/servers/ for your MCP server:
src/servers/<provider>/<service>/
__init__.py
mcp.py
outputs.py
prompts.pyFor example, to add a new "calendar" service under Google:
src/servers/google/calendar/
__init__.py
mcp.py
outputs.py
prompts.pyStep 2: Define Output Models (outputs.py)
Create Pydantic models for your tool outputs:
Step 3: Define Prompts (prompts.py)
Create prompts for your MCP server (optional):
Step 4: Create the MCP Server (mcp.py)
Create the MCP server class by extending BaseMCPServer:
Step 5: Register the MCP Server
Update src/setup/mcp.py to register your new MCP server:
from src.servers.google.calendar.mcp import CalendarMCPServer
# Add to existing imports and initializations
calendar_server = CalendarMCPServer()
MCP_PATH = {
# ...existing servers...
"calendar": calendar_server,
}The server will automatically:
Be mounted at
/<server_name>(e.g.,/calendar)Have session management handled by the lifespan context
Include authentication and context middleware
How to Add a New REST API
REST APIs are used for standard HTTP endpoints. Follow these steps to add a new API:
Step 1: Create the API Directory
Create a new directory under src/app/ for your API:
src/app/<feature>/
__init__.py
api.pyFor example, to add a "users" API:
src/app/users/
__init__.py
api.pyStep 2: Create the API Router (api.py)
Create the FastAPI router with your endpoints:
Step 3: Register the API Router
Update src/setup/api.py to include your new router:
Project Structure Overview
src/
├── main.py # FastAPI app entry point
├── setup/
│ ├── api.py # REST API route registration
│ └── mcp.py # MCP server registration
├── app/ # REST API endpoints
│ ├── health_check/
│ ├── auth/
│ └── <your_api>/
├── servers/ # MCP servers
│ ├── google/
│ │ ├── gmail/
│ │ ├── drive/
│ │ └── <your_service>/
│ ├── druling/
│ └── <your_provider>/
├── core/
│ ├── service/ # Base MCP server class
│ ├── middleware/ # Auth and context middleware
│ ├── exceptions/ # Custom exceptions
│ └── utils/ # Utility functions
└── clients/
└── backend/ # Backend API clientKey Concepts
MCP Server
Extends
BaseMCPServerfromsrc.core.serviceProvides tools (functions) and prompts for AI agents
Uses
@self._mcp.tool()decorator to register toolsUses
mcp_meta()for tool metadataAccess user context via
self.get_context()
REST API
Uses FastAPI's
APIRouterRegistered via
app.include_router()Standard REST conventions with proper status codes
Backend Client
Use
BackendClientfromsrc.clients.backend.clientto call backend servicesSupports
get(),post(),put(),delete()methodsPass
contextfor authenticated requests
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
Related MCP Servers
- AlicenseAqualityDmaintenanceA custom MCP server that provides AI applications with access to an Artificial Virtual Assistant (AVA) toolset, enabling Gmail integration and task management through natural language.1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI applications with a toolset for an Artificial Virtual Assistant (AVA) integrated with the Gmail API. It enables users to automate email management and personal tasks through secure Google OAuth authentication.1Apache 2.0
- AlicenseBqualityDmaintenanceAn MCP server for automating Google Workspace applications including Sheets, Apps Script, Drive, Docs, and Gmail. It enables users to manipulate spreadsheets, edit scripts, manage files, and send emails directly from conversational AI interfaces.31MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server integrating Google Docs, Sheets, Drive, Gmail, Calendar, and Apps Script APIs, featuring unique Apps Script support for AI-driven automation.10 npm8MIT