Skip to main content

CellarTracker MCP

Connect Claude to your CellarTracker wine cellar. Query your inventory, get drinking recommendations, analyze purchases, and evaluate new wines — all through natural conversation.

Install

Works with both Claude Desktop (mac app) and Claude Code.

Prerequisites

Install uv (a fast Python package manager). This is a one-time step:

brew install uv

Step 1: Add the marketplace

Claude Desktop: Settings > Customize > Browse plugins > + > Add marketplace from GitHub > enter slavins-co/cellartracker-mcp

Claude Code:

/plugin marketplace add slavins-co/cellartracker-mcp

Step 2: Install the plugin

Claude Desktop: Find "CellarTracker MCP" in the plugin browser and click Install.

Claude Code:

/plugin install cellartracker-mcp@cellartracker-mcp

Step 3: Set up your CellarTracker credentials

Create a credentials file (one-time setup):

mkdir -p ~/.config/cellartracker-mcp

Then create the file ~/.config/cellartracker-mcp/.env with your CellarTracker login:

CT_USERNAME=your_cellartracker_username
CT_PASSWORD=your_cellartracker_password

These are the same username and password you use at cellartracker.com. Credentials are stored only on your machine and never sent anywhere except CellarTracker's own servers.

Step 4: Restart Claude

Fully quit and reopen Claude Desktop, or restart your Claude Code session.

Try it: "What wines should I open this week?"

What you can do

Tool What it does
search_cellar Find wines by name, color, region, varietal, location, or vintage
drinking_recommendations Wines to open now, sorted by drinking window urgency
cellar_stats Collection overview — totals and breakdowns by any dimension
purchase_history Spending analysis by store, date range, or wine
get_wishlist Your wishlist with ratings, notes, and prices
refresh_data Force a fresh pull (auto-refreshes every 24 hours)

Included skills

cellartracker-data — Teaches Claude to interpret CellarTracker data: table relationships, score abbreviations, drinking windows, and query routing.

wine-purchase-evaluator — Framework for evaluating wine purchases. Two-score system (Quality + Personal Fit) with BUY/CONSIDER/PASS verdicts. Checks your cellar for redundancy, verifies pricing, and applies drinking window discipline.

To customize the evaluator for your preferences, copy skills/wine-purchase-evaluator/references/preferences-example.md to preferences.md in the same directory and edit it.

How it works

CellarTracker has no official API. This server uses their CSV export endpoint, which authenticates with your username and password over HTTPS. Data is cached locally and auto-refreshes every 24 hours.

The server can only access your data — inventory, purchases, notes, and wishlist. It cannot search CellarTracker's full wine database.

Development

For contributors or anyone who wants to run from source:

git clone https://github.com/slavins-co/cellartracker-mcp.git
cd cellartracker-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

# Set credentials
cp .env.example .env
# Edit .env with your CT login

# Test as Claude Code plugin
claude --plugin-dir .

License

MIT

Metadata

Release files for cellartracker-mcp 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cellartracker-mcp 0.1.0
File Size Uploaded
cellartracker_mcp-0.1.0.tar.gz 28.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for cellartracker-mcp 0.1.0
File Interpreter ABI Platform
cellartracker_mcp-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 42.0 kB

Release files / cellartracker_mcp-0.1.0.tar.gz

Download URL cellartracker_mcp-0.1.0.tar.gz
Size 28.0 kB
Tags Source
SHA-256 checksum
How to use checksums
1ea5f72f822c9489b7b0b99506b0a3c30d10a5f7f525595d65d0d943b82c834e
BLAKE2b-256 checksum
How to use checksums
160bf32fa567b6d00f237ad9f3b8b306573b68106d8ef3954cd6f5d1c105c7a1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 13, 2026.

Transparency log

Release files / cellartracker_mcp-0.1.0-py3-none-any.whl

Download URL cellartracker_mcp-0.1.0-py3-none-any.whl
Size 14.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
41ff1b95d2811f18b81612d44537741e6791582aeecdf67a7a42cfcb75d04770
BLAKE2b-256 checksum
How to use checksums
b88f0afd8c94626e79926846348f74b1aa753871cb64f93c260d4475d6157276
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 13, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page