Skip to main content

Set up connected applications

Databricks-provided MCPs for external services, such as system.ai.github and system.ai.slack, call third-party apps. Most work as soon as each user completes a one-time OAuth login. Some also require an administrator to configure the third-party app or your workspace network first.

This page covers that administrator setup and the compliance review to do before you enable a Databricks-provided MCP. It is separate from the per-user OAuth Login each user completes before their first call, and from the OAuth scopes each MCP requests.

Review compliance requirements​

Before you enable a Databricks-provided MCP, review the third-party app it calls and confirm that the app and your intended use meet your organization's requirements, including compliance requirements.

Databricks-provided MCPs send requests, including the data in them, to third-party apps. Some forward requests to the third-party app's own MCP server, such as Slack, GitHub, and Atlassian. Others run on Databricks and call the third-party app's API, such as Google Drive, Gmail, and Google Calendar. In both cases, the third-party app processes that data under its own terms, including its compliance, data retention, and data residency policies. Data that the third-party app returns is available to the agent and the model it uses.

Tools can also take actions in the third-party app with the signed-in user's permissions, such as sending messages or creating pull requests. To limit what an MCP can do, choose which tools it exposes and apply service policies.

General configuration​

The following steps apply to every Databricks-provided MCP. Complete each one that matches your workspace and third-party app configuration.

Allow outbound access from your workspace​

MCPs route their outbound requests through your workspace's serverless compute plane. If your workspace uses serverless egress control with Restricted access, add each MCP server's fully qualified domain name (FQDN) to the policy's Allowed domains list. For the steps, and for how to find each service's destination, see Workspace to external MCP server.

Allow Databricks in the third-party app​

If your organization restricts inbound traffic to the third-party app to an allowed set of IP addresses, such as a GitHub organization IP allowlist, add the Databricks serverless outbound IPs for your workspace's cloud and region to the app's allowlist so it accepts calls from Databricks. For the list of IP addresses, see IP addresses and domains for Databricks services and assets. For more about Databricks serverless outbound networking, see Serverless compute firewall configuration.

Additional third-party app configuration​

Two groups of administrators control whether users can sign in to a connector and what the connection can do:

  • Provider administrators: Your organization's Slack, Google Workspace, Microsoft Entra ID, or GitHub administrators decide whether users can authorize the app and which permissions it gets, such as OAuth scopes or access to GitHub repositories. They are often not your Databricks admins.
  • Databricks admins: Users with the MANAGE privilege on a connector's MCP decide which tools are available and who can call them. See Govern an MCP.

If a provider blocks sign-in or limits what a connector can access, share the steps for that provider with its administrator. After the administrator approves the app, sign out of the connector and sign in again to get the approved permissions. See Manage provider sign-in.

Approve the Databricks Genie app in Slack​

If your Slack workspace requires app approval, the Slack sign-in screen warns that the app is likely blocked. Slack can also drop permissions that an administrator hasn't approved. For example, sign-in succeeds, but the connector can't send messages.

A Slack Workspace Owner or app manager must approve the Databricks Genie app:

  1. In Slack, click Admin in the sidebar.
  2. Select Apps and workflows to open the Slack Marketplace.
  3. Click Browse, then search for and select Databricks Genie.
  4. Review the requested permissions and click Approve. The Send messages on a user's behalf permission (chat:write) lets users send messages through the connector.

If a user already requested the app, the Workspace Owner or app manager can approve the pending request instead. See Manage app approval for your workspace.

When Databricks adds a permission to the connector, Slack asks for approval again. Until the new permission is approved, sign-in fails or Slack drops the new permission.

When you sign in again, check the actions that Databricks Genie can take on the Slack sign-in screen. The list should include sending messages. If the connector still can't send messages, ask a metastore admin or another user with MANAGE on system.ai.slack to check its tools:

  1. In Unity Gateway, select MCPs and open system.ai.slack.
  2. On Overview, click Edit tools.
  3. Confirm that the tools that send messages are selected, then click Save changes.

See Choose available tools.

Allow the connectors in Google Workspace​

If Google sign-in shows an access blocked error or says that your administrator's policy blocks the app, your Google Workspace administrator restricts which third-party apps can access Google data. The Google Drive, Gmail, and Google Calendar connectors use the same Google OAuth app, so one configuration covers all three.

A Google Workspace administrator with the Service Settings administrator privilege must configure the app:

  1. In the Google Admin console, go to Security > Access and data control > API controls.
  2. Click Manage App Access.
  3. For Configured apps, click Configure new app.
  4. Enter the client ID 645306276512-s5jbhbhff6irpdq1fpt2f21pcrf4agqs.apps.googleusercontent.com, click Search, and click the app in the search results.
  5. For Scope, leave the top organizational unit selected to configure access for all users, or click Select org units to choose specific organizational units. Click Continue.
  6. For Access to Google data, select Trusted. To allow only the scopes that the connectors request, select Specific Google data instead and add the scopes listed in Managed OAuth providers. Click Continue.
  7. Review the settings and click Finish.

The app appears in the Configured apps list with the access level you selected. See Control which apps access Google Workspace data.

Approve Microsoft 365 permissions​

The Microsoft 365 connector requests all of its Microsoft Graph permissions in a single consent. Some, such as ChannelMessage.Read.All and OnlineMeetingTranscript.Read.All, require administrator consent. Until an administrator consents for the organization, users see Need admin approval and can't sign in. For the full list, see Microsoft 365 scopes.

A Microsoft Entra ID administrator who can grant tenant-wide consent, such as a Cloud Application Administrator or Application Administrator, consents once for everyone:

  1. In Unity Gateway, select MCPs and open system.ai.microsoft_365.
  2. Click Login and sign in with the administrator account.
  3. Select Consent on behalf of your organization, then click Accept.

Other users can then sign in without the consent prompt. When Databricks adds a permission, an administrator must consent again. For more about admin consent, see Grant tenant-wide admin consent to an application in the Microsoft documentation.

To limit what the connector can do, a user with MANAGE on system.ai.microsoft_365 can remove its write tools. See Choose available tools. This doesn't change the permissions on the consent screen.

Enable GitHub write access and private repository access​

By default, the GitHub connector (system.ai.github) can read only public repositories. To access private repositories, or to make changes such as committing files or creating issues and pull requests, the repository owner or a GitHub organization administrator must:

  1. Install the Databricks GitHub connector app and grant it access to the required repositories.

  2. If the organization uses an IP allowlist, add the Databricks serverless outbound IPs for your workspace's cloud and region.

After the app is installed, users can work with the granted repositories through the connector, within their own GitHub permissions.