# Databricks L1 · Needs a person Databricks is a data and AI platform. **Can an AI agent use Databricks? No.** Our agent couldn't get into Databricks on its own. Category: Data warehouses · Connects by: API, CLI, SDK · Agent payments: None found · Driven: 26 Oct 2026 **How to connect** - CLI install: `pipx install databricks-cli` (documented). Source: https://pypi.org/project/databricks-cli/ - Docs page: `https://www.databricks.com/databricks-documentation` (tested in our drive). Source: https://www.databricks.com/databricks-documentation **Level 1: Needs a person.** Agents can't get in on their own. - Got in by: A person sets it up (Not on its own in its last 2 drives) - Got as far as: Sign up (Use, Pay and Leave not reached) - To reach L2: Let an agent sign up on its own. 2 drives on one day, awaiting confirmation [What the levels mean](https://agentdrives.com/method/levels?via=md) ## From finding it to leaving What an agent managed without a person, at each step. 1. **Find**: On its own. Docs it can act on: llms.txt. 589 doc pages read. 2. **Get in**: Stopped. Can't sign up. A visible Arkose Labs puzzle appears at account setup. Stopped here. 3. **Use**: Not reached. Tasks need an account. 4. **Pay**: Not reached. Buying needs an account. 5. **Leave**: Not reached. Nothing to cancel or delete. ## Getting in None of the 5 ways in worked without a person. Where it stopped: **Email and code**. A visible Arkose Labs puzzle appears at account setup. - Both kinds of agent (On a server, or in its own browser): No. Signing up needs a person: it asks for a bot check. - Signed agent (Known to Cloudflare): No. The sign-up page opens. The CAPTCHA on the form stops them too. | Way in | What happened | |---|---| | Email and code | Stopped by a CAPTCHA | | CLI code login | Stopped by a CAPTCHA | | Sign-in for apps (OAuth, MCP) | Not tried: Not part of this drive | | Added by an admin | Not tried: Not part of this drive | | A key from a person | Not tried: Needs a person's account | [How agents get past bot checks](https://agentdrives.com/guides/let-signed-agents-past-your-bot-check.md?via=md) ## What an agent can do with Databricks No task was tried: our agent couldn't get into Databricks. Core tasks Databricks offers an agent: - Run a SQL query on lakehouse data (API, CLI) - Create and manage a database/catalog schema (API, CLI) - Create a managed table (API, CLI) - Build and run an ETL pipeline (Lakeflow) (API, CLI) - Orchestrate jobs/workflows on a schedule or trigger (API, CLI) - Ingest data from a source into the lakehouse (Lakeflow Connect) (API, CLI) - Deploy a model or AI agent as a serving endpoint (API, CLI) - Build a conversational analytics agent over data (Genie) (API, MCP) - Create an AI/BI dashboard over query data (API) - Run a vector search over embedded data (AI Search) (API) What it can't do, and why: - Run any of the ten core tasks: They all need a workspace, which could not be created. 20 more tasks it offers: - Run a notebook or code in a collaborative workspace (API, CLI) - Set row- and column-level security policies on a table (API) - View column-level lineage for a data or AI asset (API) - Monitor data quality on a table (API) - Query an external database through federation (API) - Share live data with another organization without copying it (API, CLI) - Train or fine-tune a model (API) - Create text embeddings for data (API) - Call an LLM/model through a governed gateway (API) - Evaluate AI agent output quality with AI judges (API) - Parse and extract data from documents (Document Intelligence) (API) - Build and deploy a custom data/AI application (Databricks Apps) (API, CLI) - Back up and restore a serverless Postgres database (Lakebase) (API) - Analyze shared data across parties in a clean room (Web app) - Discover and acquire data/AI assets from a marketplace (Web app) - Read the audit log for workspace activity (API) - Resize or scale compute for a cluster or warehouse (API, CLI) - Create an API token/service principal for programmatic access (API, CLI) - Configure SSO/SAML for workspace sign-in (Web app) - Read usage and cost metrics across the account (API) **Surface audit:** 2179 documented operations, 7 run, 7 passed, 2085 blocked (sandbox or plan limits), 87 left out to stay safe. ## How an agent connects API, CLI, SDK and llms.txt found. Agent surfaces: API documented · MCP tested · CLI tested · SDK documented · Docs tested · Agent payments none found. Issues found: 1. - **MCP server**: 2 tested. A server for searching the docs only. (18 tools across its docs) - **API**: Listed, not tested. REST, 1,060 operations in the machine-readable reference (docs.databricks.com/api/llms.txt) (1,060 operations across its docs) - **OpenAPI**: None found. - **CLI**: 4 tested. Databricks CLI v1.22.1. (1,084 commands across its docs) - **SDK**: Listed, not tested. Python, Java, Go, JavaScript, R SDKs documented. (10 methods across its docs) - **llms.txt**: Yes. https://www.databricks.com/llms.txt - **Agent payments**: None found. The checkout wasn't reached: Pay-as-you-go. - **Docs**: No gaps in what we read. Covers getting started, auth, error codes and code examples. https://www.databricks.com/databricks-documentation (589 of 38,106 pages read) [The standards](https://agentdrives.com/standard) ## Tips for agent builders - Read the REST reference as Markdown: docs.databricks.com/api/llms.txt lists every operation page, and each /v1/.md gives the method and path. - Add the keyless docs MCP at https://developers.databricks.com/api/mcp; it speaks MCP 2025-11-25, so start with initialize. - Once a person has made the workspace, run 'databricks auth login' (OAuth U2M with a localhost:8020 callback) or use a PAT from 'databricks tokens create'. ## How Databricks compares In Data warehouses: 2 of the 7 products we drove in Data warehouses are higher; 4 others share L1. - [ClickHouse Cloud](https://agentdrives.com/tools/clickhouse.md?via=md): L4, Gets in on its own - [MotherDuck](https://agentdrives.com/tools/motherduck.md?via=md): L4, Gets in on its own - **Databricks** (this page): L1, Can't sign up on its own - [Firebolt](https://agentdrives.com/tools/firebolt.md?via=md): L1, Can't sign up on its own - [Snowflake](https://agentdrives.com/tools/snowflake.md?via=md): L1, Can't sign up on its own - [Starburst](https://agentdrives.com/tools/starburst.md?via=md): L1, Can't sign up on its own - [Tinybird](https://agentdrives.com/tools/tinybird.md?via=md): L1, Can't sign up on its own [All 7 in Data warehouses](https://agentdrives.com/categories/data-warehouses?via=md) Sorted by level, then work done, then time to the first call. [How we rank](https://agentdrives.com/method?via=md#order) On our standard (23 criteria: against other data warehouses products where we measured 5 or more, otherwise against every product we measured): - [Errors say what to do next](https://agentdrives.com/standard#err-03): **The best result** All 4 others (data warehouses products) lower. - [A request id on every answer](https://agentdrives.com/standard#err-07): **The best result** All 5 others (data warehouses products) lower. - [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Ahead of most** 4 of 5 others (data warehouses products) lower, 1 the same. - [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Ahead of most** 51 of 65 others (every product) lower, 14 the same. - [A path written for agents](https://agentdrives.com/standard#docs-10): **Ahead of most** 4 of 6 others (data warehouses products) lower, 2 the same. - [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Ahead of most** 4 of 6 others (data warehouses products) lower, 2 the same. - [A tool list that fits](https://agentdrives.com/standard#mcp-11): **Ahead of most** 33 of 65 others (every product) lower, 32 the same. - [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with most** 4 of 6 others (data warehouses products) the same, 2 lower. - [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with most** 3 of 4 others (data warehouses products) the same, 1 lower. - [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with most** 61 of 65 others (every product) the same, 4 lower. - [Real status codes](https://agentdrives.com/standard#err-01): **The same as all** 5 others (data warehouses products). - [Export before leaving](https://agentdrives.com/standard#leave-03): **Level with most** 4 of 6 others (data warehouses products) the same, 1 lower, 1 higher. - [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 5 others (data warehouses products). - [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Level with most** 39 of 65 others (every product) the same, 10 lower, 16 higher. - [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with most** 5 of 6 others (data warehouses products) the same, 1 higher. - [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with most** 44 of 65 others (every product) the same, 1 lower, 20 higher. - [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind most** 16 of 31 others (every product) higher, 11 the same, 4 lower. - [Structured results](https://agentdrives.com/standard#mcp-08): **Behind most** 22 of 36 others (every product) higher, 14 the same. - [Truthful annotations](https://agentdrives.com/standard#mcp-07): **Behind most** 48 of 65 others (every product) higher, 17 the same. - [Prices an agent can read](https://agentdrives.com/standard#find-06): **Behind most** 5 of 6 others (data warehouses products) higher, 1 the same. - [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Behind most** 5 of 6 others (data warehouses products) higher, 1 the same. - [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Behind most** 5 of 6 others (data warehouses products) higher, 1 the same. - [Errors a program can read](https://agentdrives.com/standard#err-02): **The lowest result** All 4 others (data warehouses products) higher. [How each criterion is graded](https://agentdrives.com/standard) ## For the team behind Databricks **7 things to fix for agents.** Agent blockers: 1 found · Agent surfaces: no issues found. Safety review: 1 issue found. Agents get stuck at Get in. Prove Databricks is yours, then see where each issue is, read your safety findings and ask for a free drive after a fix. How to fix each one comes with the Audit. - Find: Clear - Get in: Blocks agents - Use: Not reached - Pay: Not reached - Leave: Not reached [Claim Databricks, free](https://agentdrives.com/app/products?add=databricks.com&ref=listing) · [What a drive covers](https://agentdrives.com/method?via=md) ## Where Databricks fits - Category: [Data and storage](https://agentdrives.com/categories/data?via=md), [Data warehouses](https://agentdrives.com/categories/data-warehouses?via=md) - Wall: [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (kept our agent out), [Arkose Labs bot check](https://agentdrives.com/vendors/arkose) (the check, and every product we met it at), [Let signed AI agents past your bot check](https://agentdrives.com/guides/let-signed-agents-past-your-bot-check?via=md) (fix guide) - Standards: [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents) - Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in) (stopped here), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay), [Leave](https://agentdrives.com/access/leave) - Rivals: [Firebolt](https://agentdrives.com/tools/firebolt?via=md) (L1), [Snowflake](https://agentdrives.com/tools/snowflake?via=md) (L1), [Starburst](https://agentdrives.com/tools/starburst?via=md) (L1) ## Cited in 1 article - [CLI for AI agents: 11 of 14 databases have one](https://agentdrives.com/research/which-kinds-of-software-give-ai-agents-a-cli-or-mcp-server?via=md) Data: [JSON](https://agentdrives.com/api/tools/databricks.json?via=md) · [Markdown](https://agentdrives.com/tools/databricks.md?via=md) · [History](https://agentdrives.com/tools/databricks/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/databricks.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/databricks.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) **Found an error?** [Tell us on this page](https://agentdrives.com/tools/databricks?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).