Databricks MCP Server

by mcp-dir Your server? Claim it

answering

Databricks is answering right now. Last checked moments ago. It exposes 17 tools. Last commit 21 Aug 2026.

Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu

Uptime history 28 days of history · worst day 96%

28 days agonow

98.9%

Uptime 24h

91 of 92 checks

Tools

read from the server

1357 ms

Response time

average over 24h

Stars

last commit 21 Aug 2026

What changed 60

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 22 August 2026. No other catalogue keeps this.

13 Sep a tool changed version2 times that day

9 Sep a tool changed version

8 Sep a tool changed version

7 Sep a tool changed version

6 Sep a tool changed version

5 Sep a tool changed version

4 Sep a tool changed version

3 Sep a tool changed version3 times that day

2 Sep a tool changed version6 times that day

1 Sep a tool changed version2 times that day

and 50 more, back to 22 August 2026

Databricks does not always answer

Over the last week it answered 99.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add databricks-mcp --transport http https://api.mcp.ai/p_databricks

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "databricks-mcp": {
      "url": "https://api.mcp.ai/p_databricks"
    }
  }
}

~/.codex/config.toml

[mcp_servers.databricks-mcp]
url = "https://api.mcp.ai/p_databricks"

.cursor/mcp.json

{
  "mcpServers": {
    "databricks-mcp": {
      "url": "https://api.mcp.ai/p_databricks"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "databricks-mcp": {
      "url": "https://api.mcp.ai/p_databricks"
    }
  }
}

Available tools 17

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

databricks

databricks_cancel_statement

Cancela um ou mais statements em execução por id. Aceita lista (`statement_ids`).

databricks_current_user

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

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

Detalha uma ou mais tabelas (colunas, tipos) por nome completo `catalog.schema.table`. Aceita lista (`full_names`).

databricks_get_warehouse

Detalha um ou mais SQL warehouses por id. Aceita lista (`ids`).

databricks_list_accounts

Lista os workspaces Databricks conectados a este install — host, label.

databricks_list_catalogs

Lista os catálogos do Unity Catalog visíveis ao PAT (name, comment, owner).

databricks_list_schemas

Lista os schemas (databases) de um catálogo Unity. Informe `catalog_name`.

databricks_list_tables

Lista as tabelas de um schema Unity (name, table_type, data_source_format). Informe `catalog_name` e `schema_name`.

databricks_list_warehouses

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

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.

authenticate

authenticate

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.

connect

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.

marketplace

marketplace

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.

report

report_bug

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

show

show_version

Show the current MCP platform and adapter versions.

toolkit

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.

Endpoints

URL	Transport	State	Latency	Checked
https://api.mcp.ai/p_databricks	streamable-http	answering	1490 ms	0 min ago

Alternatives to Databricks

same job, measured the same way

Dataassist Io

by dataassistio

Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.

answering

Dot - AI Data Analyst

by zurferr

Ask data questions in natural language. Get SQL, insights, and charts from your databases.

answering

Supabase

by mcp-dir

Your Supabase account in natural language: run SQL, apply migrations, manage tables, storage, edge f

35 tools answering

Gibsonai

by gibsonai

GibsonAI MCP server: manage your databases with natural language

answering

Redash MCP

by seob717

Connect Redash to Claude -- query data, manage dashboards, and run SQL with natural language.

305 installs/wk local only

text2sql

by cpenniman12

Ask any SQL database in natural language. Agent explores schema, writes SQL, self-corrects.

83 installs/wk local only

MCP Database Server

by souhar-dya

MCP server for SQLite, PostgreSQL, and MySQL with natural language to SQL and direct SQL tooling.

local only

DataClawe — Database as a Utility

by dataclawe

AI-native database utility. Talk to your DB in plain language. No SQL. MySQL & PostgreSQL.

answering

Databricks — questions

Answers built from our own checks of this server.

What can Databricks do?

It exposes 17 tools, read directly from the server on our last check. Among them: authenticate, connect, databricks_cancel_statement, databricks_current_user, databricks_get_statement, databricks_get_table and 11 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Databricks working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 92 checks got a reply (98.9%), average response time 1357 ms. The bar chart above shows every period we have measured.

How do I connect Databricks?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Databricks need an API key?

No. Databricks completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 17 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Databricks?

It answers our handshake in 1357 ms on average, which is faster than 2% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Databricks open source?

Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.