Metabase MCP
Security scan passedLets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.

Databricks' own skills for coding agents: build apps, jobs, pipelines and Lakebase projects, then deploy them with bundles.
by Databricks· Data & analyticsUnclaimed · Yours? Claim it
4 images
About
The Databricks plugin is Databricks' own plugin for coding agents. Its skills teach your agent how to build on Databricks with the Databricks CLI, from apps, jobs and pipelines to Lakebase and Model Serving, and it adds setup and health-check commands. What its skills cover - The Databricks CLI, sign-in and profiles, and finding and querying data, including through Genie - Databricks Apps in TypeScript (AppKit) or Python, and the design of dashboards and data apps - Declarative Automation Bundles (formerly Asset Bundles) for deploying resources, and Lakeflow Jobs for orchestration - Lakeflow Spark Declarative Pipelines, Structured Streaming, Lakeflow Connect and Zerobus ingestion - Lakebase Postgres, Databricks SQL, Unity Catalog, metric views and Apache Iceberg tables - Model Serving, Vector Search, Agent Bricks, AI Functions, MLflow evaluation and ML training - Moving classic-compute workloads to serverless compute What else it adds - /databricks:setup signs you in with OAuth, a personal access token or a service principal, then checks the profile - /databricks:doctor runs a read-only health check: CLI version, sign-in, workspace reachability, compute and recent job failures - Hooks that steer Databricks prompts to the right skill, add your CLI version and profile names when a session starts, and suggest a fix when a databricks command fails to sign in How to install it In Claude Code, run /plugin install databricks@claude-plugins-official, or add Databricks' own marketplace with /plugin marketplace add databricks/databricks-agent-skills. The Databricks CLI installs the skills alone with databricks aitools install; Databricks notes that the CLI and its repository carry the newest skills, since marketplace listings can lag. Good to know It's skills, commands and hooks, not an MCP server: your agent works through the Databricks CLI, which needs to be installed and signed in. For live workspace data, Databricks offers managed MCP servers that you connect separately.
Once it’s added
“Set up Databricks sign-in for my workspace.”
“Check my Databricks CLI, sign-in and recent job failures.”
“Build a Databricks app with a dashboard of our sales data.”
“Deploy this job to production with a Declarative Automation Bundle.”
“Create a Lakeflow pipeline that ingests streaming order events.”
“Migrate this classic-compute job to serverless.”
Before you add it
Reads only
Your Databricks CLI version, profiles and sign-in state, when a session starts · Workspace data and job runs, through the Databricks CLI
Makes changes · your agent can ask first
Writes app, job, pipeline and bundle code in your project · Deploys and changes Databricks resources through the CLI, with your permissions · Sets up a Databricks CLI sign-in profile
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
No reviews yet. Used Databricks plugin? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add anthropics/claude-plugins-official /plugin install databricks@claude-plugins-official
Scanned and passed · checked 6 h ago
Nobody has shared how they use Databricks plugin yet.
Plugins people install alongside Databricks plugin.
Scanned on every change, and again when our rules improve.
Tell us and a person on the trust team will look at it. Or email [email protected].
Plugins people install alongside Databricks plugin.
Lets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.
Equips your coding agent with a data engineer, pipeline commands and skills for Airflow, dbt, Spark and data quality.
Lets your agent query your PostHog analytics, triage errors, and create feature flags and experiments from plain-language asks.
Data analytics skills for product managers: SQL from plain English, cohort retention analysis and A/B test reads with a ship-or-stop call.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.