connect — Databricks MCP Tool
connect
(connect) is one of 17 tools on the
Databricks
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call connect from your client
- Claude Code Databricks connect run in your project directory
- Claude Desktop Databricks connect ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Databricks connect ~/.cursor/mcp.json
- VS Code Databricks connect .vscode/mcp.json
- Zed Databricks connect ~/.config/zed/settings.json
- Windsurf Databricks connect ~/.codeium/windsurf/mcp_config.json
- Cline Databricks connect ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Databricks connect ~/.gemini/settings.json
- Grok Databricks connect .mcp.json (in your project root)
- ChatGPT Databricks connect Settings → Connectors → Advanced → Developer mode
- Claude.ai Databricks connect Settings → Connectors → Add custom connector
- LangChain Databricks connect pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http databricks-mcp https://api.mcp.ai/p_databricksOther tools on this server
- databricks_list_accounts
- databricks_current_user
- databricks_list_warehouses
- databricks_get_warehouse
- databricks_run_sql
- databricks_get_statement
- databricks_cancel_statement
- databricks_list_catalogs
- databricks_list_schemas
- databricks_list_tables
- databricks_get_table
- show_version
- report_bug
- toolkit_info
- marketplace
- authenticate
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.