# Databricks — MCP server on mcp.ai
> Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running queries, and explore Unity Catalog (catalogs, schemas, tables and columns), via the official workspace REST API. Connect with your workspace URL and a Personal Access Token (PAT).

By: mcp.ai · official
Page: https://mcp.ai/databricks

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_databricks?ms=1785595200000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/databricks/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/databricks/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/databricks/skill.md
Postman collection (v2.1): https://mcp.ai/databricks/postman.json

## Tools
- databricks_cancel_statement(statement_ids: string[], account?: string) — Cancela um ou mais statements em execução por id. Aceita lista (`statement_ids`).
- databricks_current_user(account?: string) — Identifica o usuário do PAT no workspace (whoami via SCIM Me). Útil pra confirmar qual conta/host está conectado e validar o token.
- databricks_get_statement(statement_ids: string[], account?: string) — Status + resultado de um ou mais statements por id (polling de queries longas que voltaram PENDING/RUNNING do run_sql). Aceita lista (`statement_ids`).
- databricks_get_table(full_names: string[], account?: string) — Detalha uma ou mais tabelas (colunas, tipos) por nome completo `catalog.schema.table`. Aceita lista (`full_names`).
- databricks_get_warehouse(ids: string[], account?: string) — Detalha um ou mais SQL warehouses por id. Aceita lista (`ids`).
- databricks_list_accounts(account?: string) — Lista os workspaces Databricks conectados a este install — host, label.
- databricks_list_catalogs(account?: string) — Lista os catálogos do Unity Catalog visíveis ao PAT (name, comment, owner).
- databricks_list_schemas(catalog_name: string, account?: string) — Lista os schemas (databases) de um catálogo Unity. Informe `catalog_name`.
- databricks_list_tables(catalog_name: string, schema_name: string, account?: string) — Lista as tabelas de um schema Unity (name, table_type, data_source_format). Informe `catalog_name` e `schema_name`.
- databricks_list_warehouses(account?: string) — Lista os SQL warehouses do workspace (id, name, state, cluster_size, warehouse_type). Use o `id` em databricks_run_sql (ou deixe o run_sql escolher um RUNNING automaticamente).
- databricks_run_sql(statement: string, warehouse_id?: string, catalog?: string, schema?: string, parameters?: object[], row_limit?: integer, wait_timeout?: string, on_wait_timeout?: string, account?: string, warehouse_ids?: string[]) — Executa uma instrução SQL num SQL warehouse (Statement Execution API). Retorna colunas + linhas quando termina dentro do wait_timeout; senão devolve statement_id + state pra polling via databricks_get

## Example prompts
- "List my Databricks SQL warehouses"
- "Run: SELECT count(*) FROM samples.tpch.lineitem"
- "What catalogs and tables exist in Unity Catalog?"

## Links
Docs: https://mcp.ai/docs/mcps/databricks
Website: https://mcp.ai/mcps/databricks