npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@og-mcp/databricks-mcp

v0.1.0

Published

Production-grade Model Context Protocol server for Databricks (stdio + Streamable HTTP).

Readme

Databricks MCP Server

A production-grade Model Context Protocol server for Databricks. Exposes the Databricks REST API as MCP tools over stdio (local) and Streamable HTTP (hosted/multi-user).

  • TypeScript (ESM, Node 20+), REST-only over the Databricks API
  • Three auth options: PAT, OAuth M2M (service principal), and HTTP per-user token passthrough
  • Per-tool RBAC, destructive-op guard, secret redaction, structured logging, retry + per-host circuit breaker
  • Covers the full developer surface plus the databrickslabs/mcp specialties (Unity Catalog, Vector Search, Genie)

Status: All phases complete — 107 tools across 13 domains, plus 4 resources and 4 prompts:

  • clusters (12) · jobs (13) · warehouses (7) · sql (3, statement execution)
  • workspace (6, notebooks/folders) · dbfs (6) · repos (5)
  • catalog (22, Unity Catalog: catalogs/schemas/tables/volumes/functions/models/grants)
  • secrets (6) · pipelines (8, Delta Live Tables) · serving (5, model serving)
  • ml (10, Vector Search + Genie) · identity (5, SCIM)
  • Resources: databricks://clusters, …/jobs, …/catalogs, databricks://catalog/{c}/schema/{s}/tables
  • Prompts: explore-data, run-and-monitor-job, diagnose-failed-run, ask-genie

1. Prerequisites

  • Node.js ≥ 20
  • A Databricks workspace URL and either a PAT or a service principal (client ID + secret with OAuth)

2. Install & configure

cd "E:\MCP Servers\databricks-mcp-server"
npm install
cp .env.example .env   # PowerShell: Copy-Item .env.example .env

Minimum for local use with a PAT:

DATABRICKS_HOST=https://adb-1234567890.12.azuredatabricks.net
AUTH_MODE=pat
DATABRICKS_TOKEN=dapi...
DATABRICKS_DEFAULT_WAREHOUSE_ID=   # optional, for databricks_execute_sql
DATABRICKS_DEFAULT_CATALOG=        # optional

Auth modes

| AUTH_MODE | Needs | Notes | |---|---|---| | pat | DATABRICKS_TOKEN | Personal access token. Simplest. | | oauth | DATABRICKS_CLIENT_ID, DATABRICKS_CLIENT_SECRET | Service principal (M2M). Token minted at {host}/oidc/v1/token. Deployment path. |

On the HTTP transport, if a caller sends Authorization: Bearer <their-databricks-token> and ALLOW_TOKEN_PASSTHROUGH=true, that token is used for the request (per-user multi-tenant) — no shared identity needed.

3. Build & run

npm run build && npm start            # stdio (default)
node dist/index.js --transport http   # Streamable HTTP on PORT (default 3200)

4. Connect a client (npx)

{
  "mcpServers": {
    "databricks": {
      "command": "npx",
      "args": ["-y", "databricks-mcp-server"],
      "env": {
        "DATABRICKS_HOST": "https://adb-1234567890.12.azuredatabricks.net",
        "AUTH_MODE": "pat",
        "DATABRICKS_TOKEN": "dapi..."
      }
    }
  }
}

Verify with the databricks_current_user tool (confirms auth + connectivity).

5. Scripts

| Script | Purpose | |---|---| | npm run build | Compile TypeScript → dist/ | | npm start / start:http | Run compiled server (stdio / HTTP) | | npm run dev / dev:http | Watch-mode dev (tsx) | | npm run typecheck · lint · test · ci | Quality gates |

6. Architecture

transport (stdio | http)
  → server (McpServer + registry)
    → dispatch (RBAC · destructive guard · audit · error envelope)
      → domain tools (Zod schemas)
        → domain services
          → DatabricksClient (REST + retry + circuit breaker)
            → credential (PAT | OAuth M2M | HTTP passthrough)

Each Databricks area is a self-contained module under src/domains/<area>/ exporting a DomainModule. To add an area, create the module and append it to domains in src/server.ts.

Full walkthrough: see docs/END_TO_END_FLOW.md for how a request travels through every layer.