Databricks-provided MCPs

Databricks provides MCPs in the system.ai schema for data and external services. Choose an MCP below, then connect your agent. You don't need to host or register a server.

Each MCP is a Unity Catalog securable invoked through Unity Gateway. You can govern who invokes them with grants and govern individual calls with policies.

MCP server URL

For any system.ai MCP, use this URL:

Text

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

Replace <workspace-hostname> with your workspace hostname and <mcp-name> with the full name from the tables below, such as system.ai.dbsql.

Databricks data and tools

Unity Gateway Beta

To use system.ai.dbsql, system.ai.sandbox, or system.ai.web_search, an account admin must enable the Unity Gateway beta from the account console Previews page. See Manage account previews.

The Genie One MCP is generally available.

MCP	Description
system.ai.genie_one_mcp	Recommended for natural-language analytics across your workspace. Answers questions with Genie One, grounded in Genie Ontology.
system.ai.dbsql	Runs specific SQL queries for development and data engineering 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.
system.ai.sandbox	Runs Python, SQL, or shell code in an isolated environment.

MCP	Description
system.ai.genie_one_mcp	Recommended for natural-language analytics across your workspace. Answers questions with Genie One, grounded in Genie Ontology.
system.ai.dbsql	Runs specific SQL queries for development and data engineering 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.
system.ai.sandbox	Runs Python, SQL, or shell code in an isolated environment.

Genie One MCP versus Databricks SQL MCP servers

For analytics use cases, start with the Genie One MCP server. Genie resolves business terms, metric definitions, and table relationships through Genie Ontology, your governed semantic layer. This produces more accurate answers than an agent writing SQL directly against raw tables.

Use the Databricks SQL MCP server when you need to run a specific query you already wrote, such as validating syntax or authoring a pipeline.

External services

If a tool asks you to sign in, open the login link returned by the MCP, authorize access to your provider account, and retry the call. If your organization requires approval, share the app name from the consent screen with your administrator.

MCP	Connects to
system.ai.slack	Slack MCP server
system.ai.github	GitHub MCP server
system.ai.atlassian	Jira and Confluence through the 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	SharePoint, Outlook, and Teams through Microsoft Graph

MCP	Connects to
system.ai.slack	Slack MCP server
system.ai.github	GitHub MCP server
system.ai.atlassian	Jira and Confluence through the 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	SharePoint, Outlook, and Teams through Microsoft Graph

For the permissions each MCP requests, see Managed OAuth providers. Verify that the provider and your intended use meet your organization's compliance requirements.

GitHub private repositories

By default, system.ai.github can access only public repositories. A GitHub organization administrator must:

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

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

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

Connect your agent

Open Unity Gateway in your workspace and select MCPs. Copy the MCP name, such as system.ai.github, and follow your setup guide:

• Claude Code, Codex, Cursor, and other coding agents
• Python agents

For clients that require a server URL, use the URL pattern above.

For sign-in, permissions, and connection errors, see MCP authentication and networking.

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.

Legacy workspace endpoints

Existing integrations can continue to use these workspace MCP endpoints. For new Genie One and Databricks SQL connections, use the system.ai MCPs listed above.

note

Legacy workspace endpoints bypass Unity Gateway. Their calls do not appear in Unity Gateway tracing tables, and they do not support MCP-level Unity Catalog grants, policies, or guardrails. Access is controlled by permissions on the underlying resources, such as tables, functions, indexes, and SQL warehouses.

For these legacy URLs, a workspace administrator must enable Managed MCP Servers on the workspace Previews page. See each server's page for its release status.

Use the full server URL below in your MCP client. When using OAuth, request the listed scope.

Server	Server URL	OAuth scope
Genie Agent	https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}	genie
AI Search	https://<workspace-hostname>/api/2.0/mcp/ai-search/{catalog}/{schema}/{index_name}	ai-search
Databricks SQL	https://<workspace-hostname>/api/2.0/mcp/sql	sql
Unity Catalog functions	https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}/{function_name}	unity-catalog

Server	Server URL	OAuth scope
Genie Agent	https://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}	genie
AI Search	https://<workspace-hostname>/api/2.0/mcp/ai-search/{catalog}/{schema}/{index_name}	ai-search
Databricks SQL	https://<workspace-hostname>/api/2.0/mcp/sql	sql
Unity Catalog functions	https://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}/{function_name}	unity-catalog

Replace the placeholders with values from your workspace:

• Workspace hostname: Open your workspace and copy the hostname from the browser address bar, without https://, the path, or query parameters. See Find your workspace URL.
• Genie space ID: Open the Genie Agent and copy the space ID from its Settings tab.
• Catalog, schema, and index or function name: Open Catalog and find the index or function. Use the parts of its full name in the URL. For example, main.tools.lookup_customer becomes main/tools/lookup_customer.

Recommended paths for new agents

The SDK and toolkit options below are for Python agents. For native tools in coding agents, use an MCP connection.

Legacy MCP or tool	Recommended approach	What it does
Genie Agent MCP	AI Bridge tool examples	Queries the same curated Genie Agent from Python. For broader analytics, use the Genie One MCP.
Databricks SQL MCP	Databricks SQL MCP (system.ai.dbsql)	Runs SQL through Unity Gateway.
AI Search MCP	AI Bridge retriever tools	Queries your AI Search indexes directly from Python.
Unity Catalog functions MCP	UCFunctionToolkit	Calls your registered functions directly from Python.
Code interpreter (system.ai.python_exec) through the functions MCP	system.ai.sandbox (Unity Gateway Beta)	Runs Python, SQL, or shell code through MCP.

Legacy MCP or tool	Recommended approach	What it does
Genie Agent MCP	AI Bridge tool examples	Queries the same curated Genie Agent from Python. For broader analytics, use the Genie One MCP.
Databricks SQL MCP	Databricks SQL MCP (system.ai.dbsql)	Runs SQL through Unity Gateway.
AI Search MCP	AI Bridge retriever tools	Queries your AI Search indexes directly from Python.
Unity Catalog functions MCP	UCFunctionToolkit	Calls your registered functions directly from Python.
Code interpreter (system.ai.python_exec) through the functions MCP	system.ai.sandbox (Unity Gateway Beta)	Runs Python, SQL, or shell code through MCP.

For the system.ai MCPs, use the Unity Gateway URL and the ai-gateway OAuth scope. Review the MCP's access requirements before switching.

Workspace endpoint pricing

• Unity Catalog functions use serverless general compute pricing.
• Genie Agents and Databricks SQL use Databricks SQL pricing.
• AI Search indexes use AI Search pricing.