Home / MCP registry index / io.github.mcp-dir/databricks-mcp
Databricks
io.github.mcp-dir/databricks-mcp in the official MCP registry.
Endpoint https://api.mcp.ai/p_databricks. Source: github.com/mcp-dir/databricks-mcp.
The registry describes it as: Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu
We read its 17 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
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 connect toolkit_info marketplace authenticate
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-mcp-dir-databricks-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.