What is the Google Workspace MCP Server?

The Google Workspace MCP Server integrates Google Workspace services (Calendar, Drive, Gmail, and Docs) with AI assistants and other applications using the Model Context Protocol (MCP). This allows AI systems to access and interact with user data from Google Workspace applications securely and efficiently.

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. It enables AI models to interact with external data sources in a structured and secure manner.

What Google Workspace services are supported?

The server supports Google Calendar, Google Drive, Gmail, and Google Docs.

What is OAuth 2.0 Authentication?

OAuth 2.0 is a secure authentication method used to connect to Google APIs using user-authorized credentials with automatic token refresh.

How do I install the Google Workspace MCP Server?

You can install the server by cloning the repository, creating a virtual environment, and installing dependencies using uv or pip.

What are the prerequisites for installation?

You need Python 3.12+, the uv package installer (or pip), and a Google Cloud Project with OAuth 2.0 credentials enabled for the required APIs.

How do I configure the server?

You need to create OAuth 2.0 Credentials in the Google Cloud Console, enable the Google Calendar API, Google Drive API, Gmail API, and Google Docs API for your project, and download the OAuth client credentials as client_secret.json.

How do I start the server?

You can start the server in HTTP mode or using mcpo. HTTP mode runs the server with an HTTP transport layer on port 8000, while mcpo exposes the server as an OpenAPI endpoint.

What is mcpo?

mcpo is a tool that allows you to expose the server as an OpenAPI endpoint for integration with tools like Open WebUI.

How do I connect to the server?

You can connect to the server using mcpo for OpenAPI Spec Access or in HTTP mode by sending MCP JSON requests directly to http://localhost:8000.

How do I integrate with Open WebUI?

Create a config.json file with the necessary configuration and start the mcpo server, then configure Open WebUI to use the server’s URL.

What is first-time authentication?

The first time you call a tool that requires Google API access, the server will initiate the OAuth 2.0 flow, requiring you to log in to your Google account and grant the requested permissions.

What tools are available?

The available tools include list_calendars, get_events for Calendar, search_drive_files, get_drive_file_content, list_drive_items, create_drive_file for Google Drive, search_gmail_messages, get_gmail_message_content for Gmail, and search_docs, get_doc_content, list_docs_in_folder, create_doc for Google Docs.

How do I add new tools?

Choose or create the appropriate module, import necessary libraries, define an async function for your tool logic, decorate the function with @server.tool("your_tool_name"), and implement the logic to call the Google API.

What are the security notes?

Ensure that client_secret.json is not committed to version control, protect user tokens, use HTTPS for the OAuth callback URI in production, and consider using the --api-key option for mcpo.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform that helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.

How does UBOS enhance Google Workspace MCP Server integration?

UBOS simplifies the deployment and management of the Google Workspace MCP Server, provides a secure environment for running the server, offers tools for monitoring its performance, and enables you to orchestrate AI Agents that utilize the server.

What are the benefits of using UBOS with Google Workspace MCP Server?

Simplified deployment and management, enhanced security, improved monitoring and performance, and orchestration capabilities.