Skip to content

Aembit supports the official Google Workspace MCP servers, which let AI Agent: A software workload that authenticates to systems, requests credentials, and accesses resources, either on behalf of a person or on its own. Aembit secures AI agents with the same identity-first model it uses for any workload. User-driven agents such as Claude Desktop also carry a blended identity that ties access to both the user and the agent.Learn more read Drive files, calendar events, and contacts through Model Context Protocol: A standard protocol for AI agent and server interactions that defines how AI assistants communicate with external tools and data sources.Learn more(opens in new tab) tools.

This page describes how to configure three Google Workspace MCP Server: A server that implements the Model Context Protocol to provide tools, resources, or data to AI agents and MCP clients.Learn more(opens in new tab): Google Drive, Calendar, and People. The Aembit MCP Identity Gateway: A component that brokers MCP traffic between MCP clients and target MCP servers, validating authorization and presenting Aembit-managed credentials on each request.Learn more brokers the connection. Each user authenticates with their own Google identity, and the Gateway injects their token into MCP requests.

Before you begin, ensure you have the following:

Before you configure Google Workspace, review these requirements and behaviors specific to Google’s MCP servers.

  • Enroll in Google’s Developer Preview Program. Google’s Workspace MCP servers are available only through the Developer Preview Program. Until your organization enrolls, Google returns permission errors for every tool call. Preview enrollment also expands the data Google collects on the vendor side. Review Google’s Preview terms before you enroll.
  • Configure each service on its own. Drive, Calendar, and People each require their own GCP OAuth client, their own enabled API, and their own Aembit Credential Provider, Server Workload, and Access Policy.
  • Google Chat isn’t available. The Gateway returns an “Internal error encountered” for every Google Chat tool, so this guide doesn’t cover Chat.
  • Gmail isn’t available. This guide doesn’t cover Gmail.

Each service uses the same configuration flow but different values. Use the values for the service you’re configuring in the following steps. These scopes grant read-only access. Substitute the read/write variant (for example, https://www.googleapis.com/auth/drive instead of drive.readonly) if your agents need to modify data.

SettingValue
API to enabledrive.googleapis.com
OAuth scopehttps://www.googleapis.com/auth/drive.readonly
MCP Server URLhttps://drivemcp.googleapis.com/mcp/v1
Server Workload hostdrivemcp.googleapis.com
URL Path/mcp/v1

Repeat this section for each Google Workspace service you want to enable. Each service needs its own enabled API and its own OAuth client.

  1. In the Google Cloud console, select the project you want to use.

  2. Enable the API for your service (see Service settings). If a later tool call reports that an API “has not been used or is disabled,” enable the API named in that error too.

  3. Go to the Credentials page, click Create Credentials, then select OAuth client ID. If your project has no consent screen, configure one first: choose a User type, enter the app details, then add your service’s OAuth scope.

  4. For Application type, select Web application, enter a name, then click Create. Leave Authorized redirect URIs empty for now. You add the Aembit Callback URL after you create the Credential Provider.

  5. Copy the Client ID and Client secret, and store them for the next section.

Create an MCP User-Based Access Token Credential Provider: Credential Providers obtain the specific access credentials—such as API keys, OAuth tokens, or temporary cloud credentials—that Client Workloads need to authenticate to Server Workloads.Learn more in Aembit for the service.

  1. Log into your Aembit Tenant.

  2. Go to Credential Providers in the left sidebar and click + New.

  3. Configure the following fields:

    FieldValue
    NameA user-friendly name
    Credential TypeMCP User-Based Access Token
    MCP Server URLYour service’s MCP Server URL (see Service settings)
    Client IDThe Client ID you copied from Google Cloud
    Client SecretThe Client Secret you copied from Google Cloud
    ScopesYour service’s OAuth scope (see Service settings)
    PKCE RequiredOn

    For MCP Server URL, click Discover to populate the Authorization URL and Token URL.

  4. Click Save.

  5. Copy the read-only Callback URL from the Credential Provider.

Return to the OAuth client in the Google Cloud console.

  1. Open the Web application OAuth client you created for this service.

  2. Under Authorized redirect URIs, click Add URI, paste the Aembit Callback URL, then click Save.

  1. Return to the Credential Provider in Aembit and click Authorize.

  2. Choose your Google Account and approve access. The Credential Provider status changes to Ready when the flow completes.

  1. Go to Server Workloads in the left sidebar and click + New.

  2. Configure the following fields:

    FieldValue
    NameA user-friendly name
    HostYour service’s Server Workload host (see Service settings)
    Application ProtocolMCP
    Port443 with TLS
    URL PathYour service’s URL Path (see Service settings)
    Authentication methodHTTP Authentication
    Authentication schemeBearer
  3. Click Save.

Create an Access Policy: Access Policies define, enforce, and audit access between Client and Server Workloads by cryptographically verifying workload identity and contextual factors rather than relying on static secrets.Learn more linking your Client Workload: Client Workloads represent software applications, scripts, or automated processes that initiate access requests to Server Workloads, operating autonomously without direct user interaction.Learn more (the AI agent), the service’s MCP User-Based Access Token Credential Provider, and the service’s Server Workload. See Access Policies for details.

After a user authorizes access, the Aembit AI Access Authorized page lists each configured Google Workspace MCP Server as Ready. The AI agent can then call the corresponding MCP tools (such as listing Drive files or calendar events) through the Gateway.