Databricks
Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'connect' description lacks action verbconnect 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"databricks-mcp": {
"url": "https://api.mcp.ai/p_databricks"
}
}
}リモートエンドポイント
https://api.mcp.ai/p_databricksstreamable-httpできること
ツール一覧
ツール（17）
🟢databricks_list_accounts(account)
Lista os workspaces Databricks conectados a este install — host, label.
入力スキーマ
{
"type": "object",
"properties": {
"account": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_current_user(account)
Identifica o usuário do PAT no workspace (whoami via SCIM Me). Útil pra confirmar qual conta/host está conectado e validar o token.
入力スキーマ
{
"type": "object",
"properties": {
"account": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_list_warehouses(account)
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).
入力スキーマ
{
"type": "object",
"properties": {
"account": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_get_warehouse(ids, account)
Detalha um ou mais SQL warehouses por id. Aceita lista (`ids`).
入力スキーマ
{
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string"
}
},
"account": {
"type": "string"
}
},
"required": [
"ids"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_run_sql(statement, warehouse_id, catalog, schema, parameters, ...)
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_statement. Se `warehouse_id` não for informado, escolhe um warehouse RUNNING automaticamente. PREFIRA queries parametrizadas (`parameters`) a interpolar valores na string (proteção contra SQL injection). SQL é arbitrário (pode DML/DDL) — confirme antes de mutar dados. Bulk support: accepts warehouse_ids for batched execution.
入力スキーマ
{
"type": "object",
"properties": {
"statement": {
"type": "string"
},
"warehouse_id": {
"type": "string"
},
"catalog": {
"type": "string"
},
"schema": {
"type": "string"
},
"parameters": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"value": {
"type": "string"
},
"type": {
"type": "string"
}
},
"required": [
"name",
"value"
]
}
},
"row_limit": {
"type": "number"
},
"wait_timeout": {
"type": "string"
},
"on_wait_timeout": {
"type": "string",
"enum": [
"CONTINUE",
"CANCEL"
]
},
"account": {
"type": "string"
},
"warehouse_ids": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"statement"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_get_statement(statement_ids, account)
Status + resultado de um ou mais statements por id (polling de queries longas que voltaram PENDING/RUNNING do run_sql). Aceita lista (`statement_ids`).
入力スキーマ
{
"type": "object",
"properties": {
"statement_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"account": {
"type": "string"
}
},
"required": [
"statement_ids"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴databricks_cancel_statement(statement_ids, account)
Cancela um ou mais statements em execução por id. Aceita lista (`statement_ids`).
入力スキーマ
{
"type": "object",
"properties": {
"statement_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"account": {
"type": "string"
}
},
"required": [
"statement_ids"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_list_catalogs(account)
Lista os catálogos do Unity Catalog visíveis ao PAT (name, comment, owner).
入力スキーマ
{
"type": "object",
"properties": {
"account": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_list_schemas(catalog_name, account)
Lista os schemas (databases) de um catálogo Unity. Informe `catalog_name`.
入力スキーマ
{
"type": "object",
"properties": {
"catalog_name": {
"type": "string"
},
"account": {
"type": "string"
}
},
"required": [
"catalog_name"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_list_tables(catalog_name, schema_name, account)
Lista as tabelas de um schema Unity (name, table_type, data_source_format). Informe `catalog_name` e `schema_name`.
入力スキーマ
{
"type": "object",
"properties": {
"catalog_name": {
"type": "string"
},
"schema_name": {
"type": "string"
},
"account": {
"type": "string"
}
},
"required": [
"catalog_name",
"schema_name"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢databricks_get_table(full_names, account)
Detalha uma ou mais tabelas (colunas, tipos) por nome completo `catalog.schema.table`. Aceita lista (`full_names`).
入力スキーマ
{
"type": "object",
"properties": {
"full_names": {
"type": "array",
"items": {
"type": "string"
}
},
"account": {
"type": "string"
}
},
"required": [
"full_names"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢show_version
Show the current MCP platform and adapter versions.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡report_bug(message, context, conversation)
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
入力スキーマ
{
"type": "object",
"properties": {
"message": {
"type": "string"
},
"context": {
"default": "",
"type": "string"
},
"conversation": {
"default": "[]",
"type": "string"
}
},
"required": [
"message"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢connect
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢toolkit_info
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡marketplace(action, query, mcp_id, limit, tier_slug, ...)
The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
入力スキーマ
{
"type": "object",
"properties": {
"action": {
"default": "search",
"type": "string",
"enum": [
"search",
"describe",
"install",
"uninstall",
"subscribe",
"cancel",
"resume",
"report_bug",
"request_mcp",
"list_tools",
"invoke",
"search_prompts",
"get_prompt",
"publish_prompt"
]
},
"query": {
"default": "",
"type": "string"
},
"mcp_id": {
"default": "",
"type": "string"
},
"limit": {
"default": 10,
"type": "number"
},
"tier_slug": {
"default": "",
"type": "string"
},
"immediate": {
"default": false,
"type": "boolean"
},
"cancel_reason": {
"type": "string",
"enum": [
"too_expensive",
"missing_features",
"switched_service",
"unused",
"customer_service",
"too_complex",
"low_quality",
"other"
]
},
"cancel_comment": {
"default": "",
"type": "string"
},
"message": {
"default": "",
"type": "string"
},
"report_context": {
"default": "",
"type": "string"
},
"conversation": {
"default": "[]",
"type": "string"
},
"request_name": {
"default": "",
"type": "string"
},
"request_details": {
"default": "",
"type": "string"
},
"tool_id": {
"default": "",
"type": "string"
},
"arguments": {
"default": "{}",
"type": "string"
},
"prompt_slug": {
"default": "",
"type": "string"
},
"prompt_vars": {
"default": "{}",
"type": "string"
},
"prompt_category": {
"default": "",
"type": "string"
},
"prompt_tool": {
"default": "",
"type": "string"
},
"prompt_title": {
"default": "",
"type": "string"
},
"prompt_description": {
"default": "",
"type": "string"
},
"prompt_body": {
"default": "",
"type": "string"
},
"prompt_targets": {
"default": [],
"type": "array",
"items": {
"type": "string",
"enum": [
"claude",
"chatgpt",
"cursor",
"lovable"
]
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡authenticate(token)
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
入力スキーマ
{
"type": "object",
"properties": {
"token": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス