Is this an official Databricks MCP server?

No. It is Memtro's MCP server with Memtro's Databricks connector behind it: the connector reads Databricks through its API with the credentials you connect on Dashboard → Connections, and Databricks publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Databricks?

Not yet. Today every Databricks tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Databases and warehouses

Databricks MCP server

Databricks in any MCP client, through Memtro: Databricks does not publish this server. Memtro's Databricks connector reads Databricks through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Read-only Databricks: SQL warehouses, Unity Catalog catalogs, schemas, tables and columns, SELECT queries on a warehouse with a row cap, and jobs with their recent runs and failures.

Reads

databricks_warehousesSQL warehouses visible to the token: id, name, state (RUNNING, STOPPED, STARTING…), size, type, whether serverless, auto-stop minutes and creator.
databricks_catalogsUnity Catalog: the catalogs the token can see (name, type, owner, comment), or, with `catalog`, the schemas inside one.
databricks_tablesTables and views in one schema: full name (what databricks_query references and databricks_table_columns takes), type (MANAGED, EXTERNAL, VIEW…)…
databricks_table_columnsOne table's columns (name, type, nullable, comment, partition columns), its type, format, owner, comment and, for a view, its definition.
databricks_queryRun one read-only SQL statement (SELECT / WITH, or SHOW / DESCRIBE / EXPLAIN) on the connection's SQL warehouse.
databricks_jobsJobs in the workspace: id, name, schedule (cron and timezone, paused or not), creator and when created.
databricks_job_runsRecent job runs, newest first: state, result (SUCCESS, FAILED, TIMEDOUT, CANCELED…), the error message for failures, start and end times, duration…

Connect it

First connect Databricks on Dashboard → Connections, then add Memtro to your client once. The Databricks tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Pi

One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Databricks connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› Which jobs failed in the last 24 hours, and what did the error say?
› What tables are in prod.sales, and what columns does prod.sales.orders have?
› How many orders did we take per day last week, from prod.sales.orders?
› Is the main SQL warehouse running, and who created it?
› Show me the definition of the view analytics.finance.monthly_revenue

Questions

Is this an official Databricks MCP server?: No. It is Memtro's MCP server with Memtro's Databricks connector behind it: the connector reads Databricks through its API with the credentials you connect on Dashboard → Connections, and Databricks publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Databricks?: Not yet. Today every Databricks tool reads, searches or lists; when it gains actions, each is marked, granted by name and used only when you ask, so nothing is created, sent, updated or deleted until you say so.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.