Google Workspace offers remote Model Context Protocol (MCP) servers that allow AI agents to securely interact with Google Workspace data. By configuring the Google Workspace MCP servers, you enable AI applications like Gemini CLI, Claude, or IDEs to perform actions in Google Workspace applications like Gmail, Google Drive, Google Calendar, and Google Chat. Each Google Workspace product has its own dedicated MCP server.
The Google Workspace MCP servers provide a standardized way for AI agents to:
- Read data: Search emails, retrieve files, and list calendar events.
- Take action: Create draft emails, upload files, and schedule meetings.
- Respect security: Inherit the same permissions and data governance controls as the user.
Prerequisites
A Google Cloud project. To create a project, see Create a project.
An MCP client, like Gemini CLI.
To run the commands on this page, set up the gcloud CLI in a local development environment by following these steps:
- Install the Google Cloud CLI.
If you installed the gcloud CLI previously, make sure you have the
latest version by running
gcloud components update. - If you're using an external identity provider (IdP), sign in to the gcloud CLI with your federated identity. For more information, see Sign in to the gcloud CLI with your federated identity.
- Initialize the gcloud CLI.
- Install the Google Cloud CLI.
If you installed the gcloud CLI previously, make sure you have the
latest version by running
Configure the Google Workspace MCP servers
To use the Google Workspace MCP servers, you must enable them in your Google Cloud project and then configure your MCP client to connect to them.
Enable the APIs
To use the Google Workspace MCP servers, you must enable the following APIs in your Google Cloud project:
- Gmail API
- Google Drive API
- Google Calendar API
- Google Chat API
People API
CLI
gcloud services enable gmail.googleapis.com \
drive.googleapis.com \
calendar-json.googleapis.com \
chat.googleapis.com \
people.googleapis.com --project=PROJECT_ID
Replace PROJECT_ID with your Google Cloud project ID.
Console
Enable the APIs in the Google Cloud console:
Enable the MCP services
To enable the MCP components for each Google Workspace product, you must enable the following services in your Google Cloud project:
- Gmail MCP API
- Google Drive MCP API
- Google Calendar MCP API
- Google Chat MCP API
People MCP API
CLI
gcloud services enable gmailmcp.googleapis.com \
drivemcp.googleapis.com \
calendarmcp.googleapis.com \
chatmcp.googleapis.com \
people.googleapis.com --project=PROJECT_ID
Replace PROJECT_ID with your Google Cloud project ID.
Console
Enable the MCP services in the Google Cloud console:
Configure the Chat app
To use the Google Chat MCP server, you must configure a Chat app in your Google Cloud project.
In the Google Cloud console, search for Google Chat API, and click Google Chat API > Manage > Configuration.
Set up the Chat app:
- Clear Build this Chat app as a Google Workspace add-on. A dialog opens asking you to confirm. In the dialog, click Disable.
- In App name field, enter
Chat MCP. - In Avatar URL field, enter
https://developers.google.com/chat/images/quickstart-app-avatar.png. - In Description, enter
Chat MCP server. - Under Functionality, turn off interactive features by toggling Enable interactive features off.
- Under Visibility, select Make this Chat app available to specific people and groups in your domain and enter your email address.
- Under Logs, select Log errors to Logging.
Click Save.
To learn more about building a Chat app, see Choose a Google Chat app architecture.
Set up the OAuth consent screen
The Google Workspace MCP servers use OAuth 2.0 for authentication and authorization. You must configure the OAuth consent screen before you can create an OAuth client ID.
In the Google Cloud console, go to Google Auth Platform > Branding.
If you have already configured the Google Auth Platform, you can configure the following OAuth Consent Screen settings in Branding, Audience, and Data Access. If you see a message that says Google Auth Platform not configured yet, click Get Started:
- Under App Information, in App name, type
Workspace MCP Servers. - In User support email, select your email address or an appropriate Google group.
- Click Next.
- Under Audience, select Internal. If you can't select Internal, select External.
- Click Next.
- Under Contact Information, enter an Email address where you can be notified about any changes to your project.
- Click Next.
- Under Finish, review the Google API Services User Data Policy and if you agree, select I agree to the Google API Services: User Data Policy.
- Click Continue.
- Click Create.
- If you selected External for user type, add test users:
- Click Audience.
- Under Test users, click Add users.
- Enter your email address and any other authorized test users, then click Save.
- Under App Information, in App name, type
Click Data Access > Add or Remove Scopes. A panel appears with a list of scopes for each API that you've enabled in your Google Cloud project.
Under Manually add scopes, paste the scopes for the MCP servers you want to use:
- Gmail:
https://www.googleapis.com/auth/gmail.readonlyhttps://www.googleapis.com/auth/gmail.compose
- Google Drive:
https://www.googleapis.com/auth/drive.readonlyhttps://www.googleapis.com/auth/drive.file
- Google Calendar:
https://www.googleapis.com/auth/calendar.calendarlist.readonlyhttps://www.googleapis.com/auth/calendar.events.freebusyhttps://www.googleapis.com/auth/calendar.events.readonly
- Google Chat:
https://www.googleapis.com/auth/chat.spaces.readonlyhttps://www.googleapis.com/auth/chat.memberships.readonlyhttps://www.googleapis.com/auth/chat.messages.readonlyhttps://www.googleapis.com/auth/chat.users.readstate.readonly
- People API:
https://www.googleapis.com/auth/directory.readonlyhttps://www.googleapis.com/auth/userinfo.profilehttps://www.googleapis.com/auth/contacts.readonly
- Gmail:
Click Add to Table.
Click Update.
After selecting the scopes required by your app, on the Data Access page, click Save.
Configure your MCP client
To add the Google Workspace remote MCP server to your MCP client, follow the instructions for your client.
Gemini CLI
To add the Google Workspace remote MCP servers to your Gemini
CLI, add the server configuration to your settings.json file.
Create an OAuth 2.0 client ID and secret:
In the Google Cloud console, go to Google Auth Platform > Clients > Create Client
Select Desktop app as the application type.
Enter a Name.
Click Create and copy your Client ID and Client Secret.
Open or create the configuration file
~/.gemini/settings.json.Add the
mcpServersconfiguration tosettings.json:{ "mcpServers": { "gmail": { "httpUrl": "https://gmailmcp.googleapis.com/mcp/v1", "oauth": { "enabled": true, "clientId": "OAUTH_CLIENT_ID", "clientSecret": "OAUTH_CLIENT_SECRET", "scopes": [ "https://www.googleapis.com/auth/gmail.readonly", "https://www.googleapis.com/auth/gmail.compose" ] } }, "drive": { "httpUrl": "https://drivemcp.googleapis.com/mcp/v1", "oauth": { "enabled": true, "clientId": "OAUTH_CLIENT_ID", "clientSecret": "OAUTH_CLIENT_SECRET", "scopes": [ "https://www.googleapis.com/auth/drive.readonly", "https://www.googleapis.com/auth/drive.file" ] } }, "calendar": { "httpUrl": "https://calendarmcp.googleapis.com/mcp/v1", "oauth": { "enabled": true, "clientId": "OAUTH_CLIENT_ID", "clientSecret": "OAUTH_CLIENT_SECRET", "scopes": [ "https://www.googleapis.com/auth/calendar.calendarlist.readonly", "https://www.googleapis.com/auth/calendar.events.freebusy", "https://www.googleapis.com/auth/calendar.events.readonly" ] } }, "people": { "httpUrl": "https://people.googleapis.com/mcp/v1", "oauth": { "enabled": true, "clientId": "OAUTH_CLIENT_ID", "clientSecret": "OAUTH_CLIENT_SECRET", "scopes": [ "https://www.googleapis.com/auth/directory.readonly", "https://www.googleapis.com/auth/userinfo.profile", "https://www.googleapis.com/auth/contacts.readonly" ] } }, "chat": { "httpUrl": "https://chatmcp.googleapis.com/mcp/v1", "oauth": { "enabled": true, "clientId": "OAUTH_CLIENT_ID", "clientSecret": "OAUTH_CLIENT_SECRET", "scopes": [ "https://www.googleapis.com/auth/chat.spaces.readonly", "https://www.googleapis.com/auth/chat.memberships.readonly", "https://www.googleapis.com/auth/chat.messages.readonly", "https://www.googleapis.com/auth/chat.users.readstate.readonly" ] } } } }Replace the following:
OAUTH_CLIENT_ID: The client ID you created.OAUTH_CLIENT_SECRET: The client secret you created.
Save
settings.json.Start Gemini CLI:
geminiIn Gemini CLI, authenticate with each MCP server by running the following command:
/mcp auth gmail- When prompted, press
1to open an authentication page in your browser. If you're working over SSH, follow the instructions in the CLI. - Sign in to your Google Account.
- Review the requested OAuth scopes and click Allow.
- A message appears confirming authentication was successful.
Repeat these for each MCP server:
/mcp auth drive/mcp auth calendar/mcp auth people/mcp auth chat
- When prompted, press
In Gemini CLI, run
/mcp listto view your configured MCP servers and their tools.The response is similar to the following:
🟢 gmail - Ready (10 tools) Tools: - create_draft - create_label - get_thread - label_message - label_thread - list_drafts - list_labels - search_threads - unlabel_message - unlabel_thread 🟢 drive - Ready (7 tools) Tools: - create_file - download_file_content - get_file_metadata - get_file_permissions - list_recent_files - read_file_content - search_files 🟢 calendar - Ready (8 tools) Tools: - create_event - delete_event - get_event - list_calendars - list_events - respond_to_event - suggest_time - update_event 🟢 people - Ready (3 tools) Tools: - get_user_profile - search_contacts - search_directory_people 🟢 chat - Ready (2 tools) Tools: - search_conversations - list_messages
The remote MCP server is ready to use in Gemini CLI.
Claude
To use the Google Workspace remote MCP servers with Claude.ai or Claude Desktop, you must have the Claude Enterprise, Pro, Max, or Team plan.
To add the Google Workspace remote MCP servers to Claude, configure a custom connector with an OAuth client ID and secret.
Create an OAuth 2.0 client ID and secret:
In the Google Cloud console, go to Google Auth Platform > Clients > Create Client
Select Web application as the application type.
Enter a Name.
In the Authorized redirect URIs section, click + Add URI, and then add
https://claude.ai/api/mcp/auth_callbackin the URIs field.Click Create and copy your Client ID and Client Secret.
Configure the MCP server in Claude:
- In Claude.ai or Claude Desktop, go to Settings (or Admin settings) > Connectors.
- Click Add custom connector.
- Enter the connection details for the Google Workspace product you want to add:
- Server name: A name for the server, like
Gmail. - Remote MCP server URL: The URL for the Google Workspace product, such as one of the following:
- Gmail:
https://gmailmcp.googleapis.com/mcp/v1 - Google Drive:
https://drivemcp.googleapis.com/mcp/v1 - Google Calendar:
https://calendarmcp.googleapis.com/mcp/v1 - Google Chat:
https://chatmcp.googleapis.com/mcp/v1 - People API:
https://people.googleapis.com/mcp/v1
- Gmail:
- Server name: A name for the server, like
- In Advanced settings, enter your OAuth client ID and OAuth client secret.
- Click Add.
- Repeat these steps for each Google Workspace product you want to add.
Others
Many AI applications have ways to connect to a remote MCP server. You typically need to enter details about the server, like its name, endpoints, transport protocol, and authentication method. For the Google Workspace remote MCP servers, enter the following:
Server name:
googleworkspaceServers: Each Google Workspace product has its own server URL:
- Gmail:
https://gmailmcp.googleapis.com/mcp/v1 - Google Drive:
https://drivemcp.googleapis.com/mcp/v1 - Google Calendar:
https://calendarmcp.googleapis.com/mcp/v1 - Google Chat:
https://chatmcp.googleapis.com/mcp/v1 - People API:
https://people.googleapis.com/mcp/v1
- Gmail:
Transport: HTTP
Authentication: The Google Workspace remote MCP server uses OAuth 2.0. For details, see Learn about authentication and authorization.
For more details on connecting different types of clients, see Configure MCP in an AI application.
Test the Google Workspace MCP servers
After you configure the MCP client, you can verify the connection by running some test prompts.
Try asking your MCP client the following questions:
"According to my Google Profile, what's my name?"
The client uses
people.get_user_profileto retrieve your Google Workspace profile information."Summarize the file Marketing Plan."
The client calls
drive.search_filesto locate "Marketing Plan", then usesdrive.read_file_contentto retrieve and summarize its content."What did Ariel say in her last email about our marketing plan?"
The client filters for emails from Ariel using
gmail.search_threads, retrieves the latest thread's content withgmail.get_thread, and then summarizes it for you."Draft an email to ariel@example.com saying that I approve the marketing plan."
The client uses
gmail.create_draftto create an email in your drafts folder, allowing you to review and send it from Gmail."When is my next meeting with Ariel?"
The client checks your schedule using
calendar.list_eventsand details your next meeting with Ariel.
If the tools execute successfully and you receive relevant responses, your Google Workspace MCP servers are correctly configured.
Troubleshooting
If you encounter issues connecting to the MCP servers, you can check for errors in the OAuth logs. Ask your administrator to check the OAuth log events in the security investigation tool.
Supported products
The following Google Workspace products support Google Workspace MCP servers and offer the following tools:
Important security consideration: Indirect prompt injection
When you expose a language model to untrusted data, there is a risk of an indirect prompt injection attack. Because MCP clients like Gemini CLI have access to powerful tools and APIs through the Google Workspace MCP servers, they can read, modify, and delete data in your Google Account.
To mitigate these risks, follow these best practices:
- Only use trusted tools. Never connect Google Workspace MCP servers to untrusted or unverified applications.
- Be cautious with untrusted inputs. Avoid asking your MCP client to process emails, documents, or other resources from unverified sources. These inputs may contain hidden instructions that can hijack your session, allowing an attacker to modify, steal, or delete your data.
- Review all actions. Always carefully review the actions taken by your AI client on your behalf to ensure they are correct and align with your intentions.