Cellartracker Wine Cellar MCP
@slavins-co
Cellartracker Wine Cellar MCP について
Connect your AI assistant to your CellarTracker wine cellar. Query your inventory, get drinking recommendations, and analyze purchases and drinking history, all through natural conversation. No need to refresh your inventory, or share your tasting notes. The MCP enables AI tools
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Cellartracker Wine Cellar MCP?
Cellartracker Wine Cellar MCP connects Claude to your CellarTracker wine cellar, allowing you to query inventory, get drinking recommendations, and analyze purchases and drinking history through natural conversation. It is designed for CellarTracker users who want to interact with their wine data directly from Claude without manually refreshing exports or sharing tasting notes.
How to use Cellartracker Wine Cellar MCP?
Two install methods exist: a Desktop Extension (.mcpb) for Chat and Cowork modes, and a Claude Code Plugin for Cowork and Code modes. The Desktop Extension is installed by downloading the .mcpb file from the latest release and double-clicking it; credentials are prompted on install. The Claude Code Plugin is installed via the desktop app plugin browser or terminal commands, requiring a subsequent setup-credentials command. Both methods authenticate with your CellarTracker username and password.
Key features of Cellartracker Wine Cellar MCP
- Search your cellar by wine name, color, region, varietal, location, or vintage
- Get drinking recommendations sorted by drinking window urgency
- View collection overview with totals and breakdowns by any dimension
- Analyze purchase history by store, date range, or specific wine
- Access your wishlist, consumption history, and personal tasting notes
- Force a fresh data pull (automatically refreshes every 24 hours)
Use cases of Cellartracker Wine Cellar MCP
- Ask "What wines should I open this month?" and receive prioritized recommendations
- Search your cellar for a specific wine or style before making a purchase decision
- Review purchase history to analyze spending by store or date range
- Look up tasting notes and ratings for wines you have already consumed
- Use the wine purchase evaluator skill to assess potential new purchases against your existing inventory
FAQ from Cellartracker Wine Cellar MCP
How does authentication work if CellarTracker has no official API?
This server uses CellarTracker's CSV export endpoint, which authenticates with your username and password over HTTPS. CellarTracker does not offer OAuth, API keys, or scoped tokens, so this MCP performs read-only operations but authenticates with your full account credentials.
Where are my credentials stored?
The Desktop Extension stores credentials in your OS keychain (macOS Keychain or Windows Credential Manager). The Claude Code plugin stores them as plaintext in ~/.config/cellartracker-mcp/.env. You can also set CT_USERNAME and CT_PASSWORD as environment variables to avoid storing credentials on disk.
Can this MCP search all of CellarTracker's wine database?
No. The server can only access your personal data — inventory, purchases, notes, and wishlist. It cannot search CellarTracker's full wine database.
What data does the server cache and for how long?
Data is cached locally and auto-refreshes every 24 hours. You can also use the refresh-data tool to force a fresh pull at any time.
What transport and authentication methods are supported?
The server uses the standard MCP transport via the Claude Desktop and Claude Code interfaces. Authentication is handled by the server itself, not by MCP's auth layer — credentials are passed from the user to the server and then to CellarTracker over HTTPS. The Desktop Extension stores credentials in the OS keychain, while the Claude Code plugin uses a .env file or environment variables.
「AI とエージェント」の他のコンテンツ
Perplexity MCP Server
DaInfernalCoderA Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
コメント