Espresso Steals

Espresso gear price history: live Amazon prices, 2+ years of daily data, BUY calls at verified lows.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
80%
命名质量
95%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~841token 数(工具定义)
~1.0 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.66%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "catalog": {
      "url": "https://espressosteals.com/api/mcp"
    }
  }
}

远程端点

https://espressosteals.com/api/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_catalog(slot, query, max_price, min_price, brand, ...)

Search the espresso gear this site tracks (every result has a live Amazon price and, when it is at a genuine low, a BUY call computed from its own price history; otherwise no call). Filter by slot (the role a product plays in a setup), free-text words matched against name/brand/notes, a price band, a brand, or on-sale only. Returns up to `limit` products with price, verdict and a one-line note. Call it more than once with different filters; broaden if a search returns nothing.

输入模式

{
  "type": "object",
  "properties": {
    "slot": {
      "type": "string",
      "enum": [
        "machine",
        "grinder",
        "scale",
        "tamper",
        "water",
        "cleaning",
        "pitcher",
        "wdt",
        "funnel",
        "puckscreen",
        "basket",
        "knockbox",
        "mat"
      ],
      "description": "Restrict to one slot. Omit to search every slot."
    },
    "query": {
      "type": "string",
      "description": "Free-text words to match (any word matches), e.g. \"hand burr\", \"lever\", \"dual boiler\"."
    },
    "max_price": {
      "type": "number",
      "description": "Only products at or under this USD price."
    },
    "min_price": {
      "type": "number",
      "description": "Only products at or over this USD price."
    },
    "brand": {
      "type": "string",
      "description": "Only this brand (case-insensitive)."
    },
    "on_sale_only": {
      "type": "boolean",
      "description": "Only products at a good price today (verdict = buy)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "description": "Max results. Default 12."
    }
  }
}
🟢get_product(slug)

Full detail for one tracked product by slug: community sentiment, reference price and basis, date of the latest price observation, portafilter size (machines) or accessory size (sized accessories), superautomatic / manual-lever / hand-grinder flags, product URL and Amazon link.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "A slug from search_catalog."
    }
  },
  "required": [
    "slug"
  ]
}
🟢list_slots

The slots an espresso setup is built from (machine, grinder, scale, tamper…), with what each is for. Use the ids as search_catalog's `slot`.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢watch_price(email, slug, target_price)

Email the user when a product is at a good price (a verified low), or at or under a target price they name. Use after search_catalog/get_product when the user wants to be told when to buy. Ask the user for their email; never invent or reuse one. One watch per email per product; calling again updates the target. The first time an address is used it receives a confirmation email and the watch arms when they click it — tell the user to check their inbox. Each alert links to the product page and carries an unsubscribe link.

输入模式

{
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "description": "The user's email address, given by the user in this conversation."
    },
    "slug": {
      "type": "string",
      "description": "A slug from search_catalog or get_product."
    },
    "target_price": {
      "type": "number",
      "description": "Optional USD price to alert at or under. Omit to alert on the next verified low."
    }
  },
  "required": [
    "email",
    "slug"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具