Databricks-provided MCP Services

Databricks provides ready-to-use MCP Services in the system.ai schema. These services include workspace tools and integrations with common SaaS applications, so agents can reach these tools without hosting or registering their own MCP server.

Each service is a Unity Catalog securable invoked through Unity Gateway. Built-in services have platform-managed tools, so you cannot change their tool selection. You can govern who invokes them with grants and govern individual calls with service policies.

Workspace tools

Beta

The DBSQL, web search, and sandbox MCP Services are in Beta. The Genie One MCP Service is generally available.

MCP Service	Description
system.ai.genie_one_mcp	Answers natural-language analytics questions across your workspace with Genie One, grounded in Genie Ontology.
system.ai.dbsql	Runs SQL on a SQL warehouse using the caller's Unity Catalog and warehouse permissions.
system.ai.web_search	Searches the public web and returns a synthesized answer with citations. See Web search on Databricks.
system.ai.sandbox	Runs Python, SQL, or shell code in an isolated environment.

MCP Service	Description
system.ai.genie_one_mcp	Answers natural-language analytics questions across your workspace with Genie One, grounded in Genie Ontology.
system.ai.dbsql	Runs SQL on a SQL warehouse using the caller's Unity Catalog and warehouse permissions.
system.ai.web_search	Searches the public web and returns a synthesized answer with citations. See Web search on Databricks.
system.ai.sandbox	Runs Python, SQL, or shell code in an isolated environment.

Connected applications

MCP Service	Connects to
system.ai.slack	Slack
system.ai.github	GitHub
system.ai.atlassian	Jira and Confluence
system.ai.google_drive	Google Drive
system.ai.google_calendar	Google Calendar
system.ai.gmail	Gmail
system.ai.microsoft_365	Microsoft 365 (SharePoint, Outlook, and Teams)

MCP Service	Connects to
system.ai.slack	Slack
system.ai.github	GitHub
system.ai.atlassian	Jira and Confluence
system.ai.google_drive	Google Drive
system.ai.google_calendar	Google Calendar
system.ai.gmail	Gmail
system.ai.microsoft_365	Microsoft 365 (SharePoint, Outlook, and Teams)

For Google Drive, Gmail, Google Calendar, and Microsoft 365, each user completes a one-time OAuth login before their first call. Open the service in Catalog Explorer and click Login.

Connected applications call third-party services. Review these services to confirm they meet your enterprise requirements, including compliance requirements. To restrict which providers the services can reach, see Control network access to providers. To restrict who can invoke them, see Control who can invoke an MCP Service.

Enable GitHub private repository access

By default, system.ai.github can access only public repositories. To give it access to private enterprise repositories, a GitHub organization administrator must complete the following steps:

1. Install the Databricks GitHub connector app on your GitHub organization so it can access your private repositories.

   For AWS GovCloud, use the databricks-gh-connector-gov-cloud app instead.

2. Allowlist the Databricks serverless outbound IPs for your workspace's cloud and region. For the list of IP addresses, see IP addresses and domains for Databricks services and assets. For instructions on configuring allowed IP addresses for your GitHub organization, see Managing allowed IP addresses for your organization.

After administrator setup is complete, users in your organization can access private repositories through system.ai.github.

Invoke a service

Address a service by its Unity Gateway URL, with its fully qualified Unity Catalog name in the path:

https://<workspace-hostname>/ai-gateway/mcp-services/system.ai.<service-name>

To call a service from agent code, see Use MCP tools in an agent.

Limitations

• system.ai.web_search is not available in workspaces with HIPAA/BAA compliance enabled. It is available in supported US regions or in workspaces that allow cross-Geo processing.

• system.ai.sandbox does not have network egress.
• Connected application MCP Services call third-party MCP servers or APIs. Before using a connected application MCP Service, verify that the provider's service and your intended use meet your organization's compliance requirements:
  • system.ai.slack: Slack MCP server
  • system.ai.github: GitHub MCP server
  • system.ai.atlassian: Atlassian Rovo MCP server
  • system.ai.google_drive: Google Drive, Docs, Sheets, and Slides APIs
  • system.ai.google_calendar: Google Calendar API
  • system.ai.gmail: Gmail API
  • system.ai.microsoft_365: Microsoft Graph