From a354d2ec2b002a91b7406af5bf7cdf488e4335a6 Mon Sep 17 00:00:00 2001
From: Bei Pang <bei@noom.com>
Date: Wed, 3 Jun 2026 15:54:24 -0700
Subject: [PATCH] [DET-4499] Update readme and env comment to make install
 easier

---
 noom-mcp-server/.env.example | 15 +++++++++------
 noom-mcp-server/README.md    | 21 ++++++++-------------
 2 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/noom-mcp-server/.env.example b/noom-mcp-server/.env.example
index 25c72b5d..3a33aafc 100644
--- a/noom-mcp-server/.env.example
+++ b/noom-mcp-server/.env.example
@@ -3,7 +3,10 @@
 # Copy this file to .env and fill in the values below.
 # DO NOT commit .env to source control.
 #
-# Authentication: the server opens a browser OAuth flow on first run.
+# Authentication: at startup the server checks for a cached Databricks OAuth
+# token. If one exists the start is silent; if not, a browser tab opens to
+# complete the login flow. On headless machines, run:
+#   databricks auth login --host https://noom-prod.cloud.databricks.com
 # SP credentials are managed by an admin — no config needed here.
 # See DEVELOPMENT.md for dev/CI setup.
 
@@ -13,8 +16,8 @@ DATABRICKS_HOST=https://noom-prod.cloud.databricks.com
 # SQL execution workspace — must match DATABRICKS_HOST
 DATABRICKS_MCP_SQL_HOST=https://noom-prod.cloud.databricks.com
 
-# SQL warehouse — all queries are forced to run on this warehouse
-# Find it in Databricks UI: 
-# * SQL Warehouses → Pick your warehouse. 
-# * In the Overview, you can see the ID by the warehouse name
-DATABRICKS_WAREHOUSE_ID=<your-warehouse-id>
+# SQL warehouse — all queries are forced to run on this warehouse.
+# The default below is the shared Noom production warehouse. Override if
+# you need a different warehouse (find its ID in Databricks UI under
+# SQL Warehouses → your warehouse → Overview).
+DATABRICKS_WAREHOUSE_ID=575c0a43969584a4
diff --git a/noom-mcp-server/README.md b/noom-mcp-server/README.md
index 48f8e505..10ff85b4 100644
--- a/noom-mcp-server/README.md
+++ b/noom-mcp-server/README.md
@@ -23,34 +23,29 @@ cd databricks-ai-dev-kit/noom-mcp-server
 curl -LsSf https://astral.sh/uv/install.sh | sh
 ```
 
-**3. Authenticate to Databricks with OAuth** (PAT tokens are rejected)
-
-```bash
-databricks auth login --host https://noom-prod.cloud.databricks.com
-```
-
-**4. Create your `.env` file**
+**3. Create your `.env` file**
 
 ```bash
 cp .env.example .env
 ```
 
-Open `.env` and set `DATABRICKS_WAREHOUSE_ID` to your SQL warehouse ID.
-(Find it in the Databricks UI under **SQL Warehouses → your warehouse → Overview**.)
+The `.env` file ships with a default `DATABRICKS_WAREHOUSE_ID`. You can leave it as-is or override it with a different warehouse ID (find it in the Databricks UI under **SQL Warehouses → your warehouse → Overview**).
 
-**5. Install dependencies**
+**4. Install dependencies**
 
 ```bash
 uv sync
 ```
 
-**6. Verify the server starts**
+**5. Verify the server starts**
 
 ```bash
 uv run --env-file .env python run.py
 ```
 
-You should see the FastMCP server start without errors. Use `Ctrl-C` to stop it — your MCP client will manage the process from here.
+At startup the server checks for a cached Databricks OAuth token. If one exists the start is silent; if not, it opens a browser tab to complete the login flow. On headless machines where a browser can't open, run `databricks auth login --host https://noom-prod.cloud.databricks.com` in a terminal first.
+
+Use `Ctrl-C` to stop it — your MCP client will manage the process from here.
 
 ---
 
@@ -117,7 +112,7 @@ user's own credentials and are not affected by the patches.
 
 - Python ≥ 3.10
 - [uv](https://docs.astral.sh/uv/getting-started/installation/)
-- Databricks OAuth session (`databricks auth login` — PAT tokens are rejected at startup)
+- Databricks OAuth token (obtained automatically via browser on first start; PAT tokens are rejected)
 - READ permission on the `dbrix_mcp_secret` secret scope (provisioned by an admin)
 
 ## Environment variables