Databricks Connector
Lets Claude query and work with data in a connected Databricks workspace.
https://claude.com/connectors/databricks
By Databricks, Inc.
How to Get It
Trust Signals Auto-scanned
Not yet scanned. Learn how to check this tool yourself.
Data & Access
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
claude.com/connectors/databricks shows read+write access to Genie structured-data queries, Vector Search over unstructured data, Unity Catalog tools/data, and deterministic functions (e.g. billing calculations), via managed or custom MCP servers. Databricks' own docs (docs.databricks.com/aws/en/generative-ai/mcp/connect-external-services) state OAuth is the recommended path (scoped, automatic token refresh) with PAT as a weaker fallback restricted to managed servers only — Databricks-hosted servers require OAuth exclusively. Critically, "Unity Catalog permissions are always enforced, so agents and users can only access the tools and data they're allowed to," meaning the connector cannot exceed the underlying user's real permissions — a genuine governance model, not just a claim. The docs do note the various MCP surfaces "are in different release stages" without labeling which is GA. | Sentiment: No significant community signal found — WebSearch budget was exhausted this session (200/200, confirmed via direct query). | Ensemble: median of 74 independent doc+sentiment evaluations (official-coverage sweep 2026-07-23).
Things to check
- Setup is admin-console-driven (OAuth app creation, redirect URL configuration) — not self-serve for an end user. Databricks' own docs flag that different MCP server types sit at different release stages without stating which is GA; confirm the specific server type before enterprise rollout.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
claude.com/connectors/databricks shows read+write access to Genie structured-data queries, Vector Search over unstructured data, Unity Catalog tools/data, and deterministic functions (e.g. billing calculations), via managed or custom MCP servers. Databricks' own docs (docs.databricks.com/aws/en/generative-ai/mcp/connect-external-services) state OAuth is the recommended path (scoped, automatic token refresh) with PAT as a weaker fallback restricted to managed servers only — Databricks-hosted servers require OAuth exclusively. Critically, "Unity Catalog permissions are always enforced, so agents and users can only access the tools and data they're allowed to," meaning the connector cannot exceed the underlying user's real permissions — a genuine governance model, not just a claim. The docs do note the various MCP surfaces "are in different release stages" without labeling which is GA. | Sentiment: No significant community signal found — WebSearch budget was exhausted this session (200/200, confirmed via direct query). | Ensemble: median of 74 independent doc+sentiment evaluations (official-coverage sweep 2026-07-23).