{
  "markdown": "# Pour Picks MCP Server\n\nQuery the [Pour Picks](https://pourpicks.app/) bourbon & whiskey database from Claude, or any MCP-compatible AI client. Read-only access to 4,700+ bottles with structured tasting profiles, prices, pairings, and community ratings.\n\nPour Picks is the bourbon collector's journal for iOS — [get it on the App Store](https://apps.apple.com/us/app/pour-picks/id6764040132).\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `search_bottles` | Full-text catalog search with category, price, and proof filters |\n| `get_bottle` | Full record for one bottle (by ID or name): tasting profile, price, pairings, community ratings |\n| `find_similar` | Bottles with a similar flavor profile, ranked by shared notes and body/sweetness/char proximity |\n| `find_cheaper_alternative` | Same style, similar profile, lower price |\n| `get_recommendations` | Picks from flavor preferences + budget + occasion |\n| `compare_bottles` | Side-by-side: proof, age, price, shared and distinct flavors, ratings |\n| `trending_bottles` | What Pour Picks users are adding to their cellars right now |\n| `pour_tonight_suggestion` | A pour for tonight, from mood, occasion, and season |\n\nEvery response includes source attribution, a citation-ready summary line, links, and data freshness dates. All scoring is deterministic — no AI calls happen inside the server.\n\n## Install (Claude Desktop)\n\nRequires Node.js 18+.\n\nAdd to your `claude_desktop_config.json` (Claude Desktop → Settings → Developer → Edit Config):\n\n```json\n{\n  \"mcpServers\": {\n    \"pour-picks\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"pour-picks-mcp\"]\n    }\n  }\n}\n```\n\nRestart Claude Desktop. No API key or configuration needed — the server ships with public read-only access.\n\n### From a local checkout\n\n```json\n{\n  \"mcpServers\": {\n    \"pour-picks\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/pour-picks/mcp-server/dist/index.js\"]\n    }\n  }\n}\n```\n\n## Configuration (optional)\n\nThe server works with zero configuration using Pour Picks' public read-only key. Environment variables override the defaults:\n\n| Variable | Purpose |\n|---|---|\n| `SUPABASE_URL` | Override the database URL |\n| `SUPABASE_SERVICE_ROLE_KEY` | Internal use only — unlocks live 30-day cellar-add trending. Never distribute this key. |\n\nWithout the service key, `trending_bottles` falls back to catalog popularity and labels the method in its response (`method: \"catalog_popularity_tier\"` vs `\"cellar_adds_last_30_days\"`).\n\n## Remote endpoint (no install)\n\nStreamable HTTP for web agents and MCP clients that take a URL:\n\n```\nhttps://nqnigdqkcvrziwcbgily.supabase.co/functions/v1/mcp\n```\n\nAlso listed on [Smithery](https://smithery.ai/servers/bguillow/pour-picks) (gateway `pour-picks--bguillow.run.tools`) and the [official MCP registry](https://registry.modelcontextprotocol.io) as `io.github.bguillow-rgb/pour-picks`.\n\n## Example agent requests\n\nQuestions an agent can answer with these tools:\n\n- *\"What bourbon is similar to Eagle Rare but easier to find?\"* → `find_similar`\n- *\"Recommend a bourbon under $60 with vanilla, oak, and caramel notes.\"* → `get_recommendations` with `taste_preferences: [\"vanilla\",\"oak\",\"caramel\"], budget: 60`\n- *\"What tastes like Blanton's without the price tag?\"* → `find_cheaper_alternative`\n- *\"Compare Eagle Rare and Buffalo Trace.\"* → `compare_bottles`\n- *\"What bourbon should I pour on a cold night?\"* → `pour_tonight_suggestion` with `season: \"winter\"`\n- *\"What bottles are collectors adding right now?\"* → `trending_bottles`\n\nExample response shape (truncated):\n\n```json\n{\n  \"cheaper_alternatives\": [\n    { \"name\": \"Buffalo Trace W.L. Weller 12 Year\", \"price_usd\": 49.99,\n      \"similarity\": 0.78, \"savings_usd\": 15.0,\n      \"shared_flavors\": [\"caramel\", \"oak\"] }\n  ],\n  \"attribution\": {\n    \"source\": \"Pour Picks — The Bourbon Collector's Journal\",\n    \"links\": { \"website\": \"https://pourpicks.app/\" }\n  }\n}\n```\n\n## Development\n\n```bash\nnpm install\nnpm run dev     # run from TypeScript via tsx\nnpm run build   # compile to dist/\nnpm start       # run compiled server\n```\n\nThe server speaks MCP over stdio. Catalog access is read-only by construction: every query path issues SELECTs against tables that are publicly readable under row-level security, and it is rate-limited to 60 calls/minute.\n\n**Usage telemetry**: each tool call logs the tool name, its arguments, client name/version, duration, and success/failure to a write-only log table (insert-only under RLS; contents are not publicly readable). No user identity, account data, or conversation content is collected. Logging is fire-and-forget and never affects responses.\n\n## Publishing\n\n- **npm**: `npm publish` from this directory (the `mcpName` field in package.json links the package to the registry entry).\n- **MCP Registry**: `server.json` in this directory is the registry manifest. Publish with the [`mcp-publisher` CLI](https://github.com/modelcontextprotocol/registry) after the npm package is live: `mcp-publisher login github && mcp-publisher publish`.\n\n## Data & attribution\n\nBottle data, tasting profiles, and pairings are curated by Pour Picks. Quote freely with attribution:\n\n> Source: Pour Picks — The Bourbon Collector's Journal (pourpicks.app)\n\nCommunity rating counts are included with every rating so you can judge sample size. Freshness dates on each bottle reflect the last enrichment pass.\n",
  "bytes": 5357,
  "sha": "1832dd7197361630d4ebb4106f47407896add8b9413c09340decc7e6456e60d6",
  "repo_slug": "bguillow-rgb/pour-picks-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_bguillow_rgb_pour_picks_a786c331/readme"
}