---
title: "Databricks SQL MCP: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/databricks-sql/
description: "Run explicit SQL against Unity Catalog tables through the managed system.ai.dbsql service, with caller permissions and optional write restriction."
---

# Databricks SQL MCP: review, setup & limitations · Undominated.ai

> Run explicit SQL against Unity Catalog tables through the managed system.ai.dbsql service, with caller permissions and optional write restriction.

[← Explore all mcp servers](/mcp-servers/)

DATABASE QUERY AND ANALYSIS / Databricks

# Databricks SQL MCP

Run explicit SQL against Unity Catalog tables through the managed system.ai.dbsql service, with caller permissions and optional write restriction.

 [See setup guidance ↓](#setup)[Original source ↗](https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 2 linked sources
 Publisher Databricks
 Licence Not established
 [Read what was—and wasn’t—checked ↓](#review)

“Databricks SQL MCP server”

 [Databricks · upstream description ↗](https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Connects SQL execution to Unity Catalog and warehouse permissions rather than distributing a database credential to a local adapter.
- Documents asynchronous execution, result truncation and a policy switch for read-only operation.
- Databricks’ SQL page says this MCP server runs AI-generated SQL against Unity Catalog tables and permits reads and writes by default.
- The built-in services page says OAuth clients must request the listed scope and points readers at legacy workspace endpoints separately from the current servers.

### A good fit for

 - Validating a specific SQL query or inspecting schemas while developing a data pipeline.
- Running bounded data checks against a chosen warehouse, then polling query completion and retaining the executed SQL.
- Running warehouse SQL against Unity Catalog tables the caller can already use
- Making the SQL MCP read-only only after the documented policy flag is set, not by assuming the default

### Weigh up before choosing

 - The Unity Gateway path is beta and requires account-admin enablement. Reads and writes are allowed by default within caller permissions.
- Large results are truncated and queries complete asynchronously; use aggregates or bounded columns/rows and handle in-progress responses.
- This service executes supplied SQL without resolving business metric definitions. Databricks recommends Genie One for semantic business questions.
- The legacy /api/2.0/mcp/sql endpoint uses a different OAuth scope and bypasses Unity Gateway MCP-level controls; it is not interchangeable with the shown URL.
- Reads and writes are the default. The documented read-only configuration sets disallow_writes=true in system.ai.dbsql_policy.
- A HIPAA limitation on the built-in page is stated for system.ai.web_search, not for the SQL server, so it is not claimed here.
- No licence was stated on these pages, and none was inferred.
- This review did not execute the resource.
- The server was not called.
- Poll started queries to completion and limit rows/columns because responses can be truncated; the SQL MCP does not supply Genie-style semantic business context.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - Databricks SQL MCP setup, policy and query limitations
- Databricks-provided MCPs and legacy endpoint boundaries
- https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql
- https://docs.databricks.com/aws/en/agents/mcp-tools/built-in-mcp-services
- Round 2 reread of acquired publisher setup and permission evidence; see immutable wave review.

### Our findings

 - Current official documentation distinguishes the system.ai.dbsql Unity Gateway endpoint and ai-gateway scope from the legacy sql-scoped workspace endpoint.
- The SQL page explicitly documents write-default behaviour, read-only policy, asynchronous queries and result truncation.
- The SQL MCP page says the server runs AI-generated SQL against Unity Catalog tables from AI coding tools.
- That server permits reads and writes by default; system.ai.dbsql_policy supports disallow_writes=true for read-only operation.
- The built-in services page says to use the full server URL and, with OAuth, to request the listed scope. It also distinguishes current Databricks-provided MCPs from legacy workspace endpoints.
- The Unity Gateway SQL endpoint uses the ai-gateway OAuth scope and permits reads and writes by default; queries are asynchronous.

### Not established by this review

 - Installation, authentication and live tool execution were not tested.
- Service availability, security isolation and package/container parity with source were not tested.
- The resource was not executed and its tools were not called.
- The server was not called. A source review is not a runtime or security certification.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql)
 - Have an account admin enable Unity Gateway beta and grant the needed MCP, Unity Catalog and SQL warehouse access.
- Connect the workspace URL https://<workspace-hostname>/ai-gateway/mcp-services/system.ai.dbsql using the ai-gateway OAuth scope and the official client setup guide.
- For read-only work, set disallow_writes=true in system.ai.dbsql_policy before connecting the agent, alongside appropriate database grants.
- Start with the documented SELECT 1 AS result check, verify the actual tool call and result, and handle polling. In programmatic clients, preset warehouse_id in _meta when warehouse selection must be deterministic.
- Have an account administrator enable the Unity Gateway beta, select the SQL warehouse, and set disallow_writes=true for read-only access.

### Before you start

 - A Databricks workspace with Unity Gateway beta enabled and a usable SQL warehouse.
- An authenticated caller with the required Unity Catalog, warehouse and MCP permissions.

### Compatibility

Claude Code · Codex · Cursor · Streamable HTTP clients with Databricks authentication

### Transports

Streamable HTTP

### Hosted service

 - Executes SQL using the caller’s Unity Catalog and warehouse permissions.
- Writes are enabled unless the disallow_writes policy or underlying grants prevent them; results are returned to the connected model client.

### Cost model

Databricks SQL compute and applicable account charges apply. No rate or managed implementation redistribution licence was reviewed.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Databricks SQL MCP setup, policy and query limitations ↗](https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql) Checked 2026-10-14 https://docs.databricks.com/aws/en/agents/mcp-tools/databricks-sql Supports: install, access, limitations, bestFor, review
- [Databricks-provided MCPs and legacy endpoint boundaries ↗](https://docs.databricks.com/aws/en/agents/mcp-tools/built-in-mcp-services) Checked 2026-10-14 https://docs.databricks.com/aws/en/agents/mcp-tools/built-in-mcp-services Supports: install, limitations, access

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
