原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Lantern Works GPU Prices: daily GPU rental price comparison

作者:connormatthewdouglas版本 0.6.0i★ 2i电脑或云端官方网站 ↗
注册名称io.github.connormatthewdouglas/lantern-works-deals

安装方法

What it does

GPU rental prices checked daily, with price history and change feed; stack optimizer; AI-infra deals

  • Connects 电脑或云端
  • Account or key No key needed
  • Category 网店与支付

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度28/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应8/8上次检查时云端端点有响应
使用分48/100

质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 Lantern Works GPU Prices: daily GPU rental price comparison。按照 https://mcp.popnx.com/i/connormatthewdouglas-lantern-works-deals.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 5/5 项检查 · 你的提问会经过开发者的服务器(lantern-works-mcp.lantern-works.workers.dev) · ✓ 命令已检查 2026年11月14日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Lantern Works GPU Prices: daily GPU rental price comparison
    Remote MCP server URL · 地址https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsLantern Works GPU Prices: daily GPU rental price comparison

  4. 试一试

    用 Lantern Works GPU Prices: daily GPU rental price comparison 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Lantern Works GPU Prices: daily GPU rental price comparison,或回答中出现 Lantern Works GPU Prices: daily GPU rental price comparison 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Lantern Works GPU Prices: daily GPU rental price comparison
    Connection · 地址https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry
  3. 在聊天中选择 Lantern Works GPU Prices: daily GPU rental price comparison

    开启新聊天,输入前先从插件列表中选择 Lantern Works GPU Prices: daily GPU rental price comparison

  4. 试一试

    用 Lantern Works GPU Prices: daily GPU rental price comparison 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Lantern Works GPU Prices: daily GPU rental price comparison,或回答中出现 Lantern Works GPU Prices: daily GPU rental price comparison 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user lantern-works-deals 'https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry'
  3. 在 Claude Code 中输入 /mcp

    应能看到 Lantern Works GPU Prices: daily GPU rental price comparison 在列表中并显示已连接

  4. 试一试

    用 Lantern Works GPU Prices: daily GPU rental price comparison 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Lantern Works GPU Prices: daily GPU rental price comparison,或回答中出现 Lantern Works GPU Prices: daily GPU rental price comparison 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Lantern Works GPU Prices: daily GPU rental price comparison 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Lantern Works GPU Prices: daily GPU rental price comparison,或回答中出现 Lantern Works GPU Prices: daily GPU rental price comparison 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Lantern Works GPU Prices: daily GPU rental price comparison 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Lantern Works GPU Prices: daily GPU rental price comparison,或回答中出现 Lantern Works GPU Prices: daily GPU rental price comparison 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Lantern Works GPU Prices: daily GPU rental price comparison 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user lantern-works-deals 'https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "lantern-works-deals": {
      "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "lantern-works-deals": {
      "type": "http",
      "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}

安装在电脑上

Claude Code

claude mcp add --scope user lantern-works-deals -- uvx lantern-works-deals-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "lantern-works-deals": {
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "lantern-works-deals": {
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "lantern-works-deals": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}

需要你填写的值

  • LANTERN_DEALS_FILE env
    本地 deals.json 文件的可选路径(离线使用)。
    查看英文原文Optional path to a local deals.json (offline use).
  • LANTERN_GPU_PRICES_FILE env
    本地 gpu-prices.json 文件的可选路径(离线使用)。
    查看英文原文Optional path to a local gpu-prices.json (offline use).

说明为自动翻译,变量名保持原样;不确定时请查看原文。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
1,703/周
连接方式
电脑或云端
传输方式
stdio, streamable-http
最新版本i
0.6.0
发布到注册中心i
2026年11月3日
代码最后更新i
2026年11月19日
最近检查
2026年11月19日
作者
connormatthewdouglas
软件包
pypi: lantern-works-deals-mcp
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月19日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • compare_gpu_prices

    Compare tracked GPU rental prices for one model (e.g. 'H100', 'A100 SXM', 'RTX 4090', 'L40S'), cheapest first. If a result looks wrong, give the user its report_issue_url. Same data as https://thelanternworks.com/api/v1/gpu-prices.json. Sorted by hourly_usd ascending; each result

  • get_price_changes

    GPU rental price changes among tracked providers, each with old/new hourly price, change_pct, direction, the vendor source_url, a stable event_id (dedupe key) and rate_id. Marketplace median moves also have composition_flag (composition, price, mixed, unknown, or null) from succe

  • optimize_stack

    Cheapest suitable stack among tracked providers for monthly needs (set the quantities you need, rest 0). scrape_pages: pages/month without JS rendering. scrape_pages_js: pages/month needing JS rendering. proxy_gb: residential proxy GB/month. emails_sent: transactional emails/mont

  • optimize_agent_stack

    Estimate a monthly stack cost from a short description of the agent being built. description: free text, e.g. 'scrapes 20k JS pages/month via 5 GB residential proxies, 3k search queries, summarizes with an LLM, budget $300/mo'. Parsed deterministically (keywords/regex, no LLM) in

  • estimate_job_cost

    Cost of one GPU job (not cost per hour) among tracked providers, cheapest current compute subtotal first. gpu_family (e.g. 'H100', 'A100 80GB') or its alias gpu (same name compare_gpu_prices uses) is required; if both are given they must match, else invalid_argument. gpus_per_job

  • rebuild_quote

    Reopen a past quote. Pass the `receipt` object returned by optimize_stack, optimize_agent_stack or estimate_job_cost. Returns receipt_intact (unkeyed sha256 matches), reproduced (true only if each line's subtotal recomputes AND its rate_id and price match the pinned feed revision

  • search_deals

    Search agent work-stack deals (compute, search, email, unblock, hosting...). offer_type: verified_discount | listed_discount (not confirmed; verified_at null) | free_tier | trial | standard_referral | credit_only_referral. max_price excludes deals with unknown price. limit 1-25.

  • compare_deals

    Compare 2-5 deals side by side (price, unit, offer type, code, verification), best value first.

  • get_deal

    Get one deal's public record by id, including redeem_url and agent_instructions.

  • create_watch_key

    Hosted only, free, opt-in. Register a webhook for GPU price alerts and get an api_key plus a webhook signing secret (both shown ONCE; store them). webhook_url must be public https. email is optional contact only (no mail is sent). No payment. Stored: a hash of the key, the webhoo

  • watch_price

    Hosted only. Alert your webhook (signed POST) after the daily refresh when a tracked rate for `gpu` crosses at or below max_hourly_usd, or a change of a watched kind (down/up/new; default down) lands at or below it. Only ELIGIBLE rates match (same contract as compare/estimate): e

  • list_watches

    Hosted only. Your watches and per-key alert counts.

  • delete_watch

    Hosted only. Delete one of your watches by watch_id.

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 connormatthewdouglas 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于今天

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 978 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 13 个工具描述,未发现针对 AI 的隐藏指令

云端地址最近 4 次检查中有 4 次响应 · 最近一次 978 ms · 检查于 2026年11月19日

已公开的漏洞(OSV.dev)

OSV.dev 中没有 lantern-works-deals-mcp@0.6.0 的记录

只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月15日

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/connormatthewdouglas-lantern-works-deals.svg)](https://mcp.popnx.com/en/servers/connormatthewdouglas-lantern-works-deals)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“网店与支付”中的其他服务器比较i

  • 星标数多于此分类中其他 2947 个服务器的 94%
  • 发布到注册中心的时间比此分类中其他 2947 个服务器的 66% 更新
  • 基础检查结果等于或优于此分类中其他 2947 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Lantern Works GPU Prices: daily GPU rental price comparison 安全吗?

它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于今天,最新版本(0.6.0)于16天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:Stripe MCP, flightclaw, Trade It, Marketplace Ad Pros: Amazon Ads & Seller Central, idealo MCP Server

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Stripe MCP

MCP server integrating with Stripe - tools for customers, products, payments, and more.

作者:stripe广泛使用★ 207213个月前更新

在云端运行✓ 服务方 · stripe.com

flightclaw

Search ~300 airlines and book flights with a checkout link. OAuth sign-in by email code.

作者:flightclaw正在增长★ 862个月前更新

在云端运行✓ 服务方 · flightclaw.com

Trade It

Connect brokerage accounts to AI assistants: holdings, orders, asset lookup, and approved trading.

作者:trade-it-inc起步阶段★ 6234天前更新

在云端运行✓ 服务方 · tradeit.app

idealo MCP Server

Search products, compare prices and discover deals across 6 European markets with your AI assistant.

作者:idealo起步阶段★ 286个月前更新

在云端运行✓ 服务方 · mcp.idealo.com
与相似项目对比
本项
Lantern Works GPU Prices: daily GPU rental price comparison
Stripe MCPflightclawTrade ItMarketplace Ad Pros: Amazon Ads & Seller Centralidealo MCP Server
运行位置云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否是否否否否
基础检查5/54/44/45/54/44/4
许可证MITMITMITCC0-1.0MITMIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Lantern Works GPU Prices: MCP server for cloud GPU rental prices

Free, read-only MCP server that compares live cloud GPU rental prices (H100, H200, A100, L40S, RTX 4090/5090 and more) across tracked providers, cheapest first, with each price's vendor source page and check time. No API key.

Connect in one line

  • Hosted, no install (Streamable HTTP): https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme
  • Local (stdio, Python 3.10+): uvx lantern-works-deals-mcp

Then ask: *"What's the cheapest H100 to rent for 100 hours? Show sources."*

thelanternworks.com · Receipts

Connect your client

Hosted URL: https://lantern-works-mcp.lantern-works.workers.dev/mcp (?ref= only tags which snippet was used). Local command: uvx lantern-works-deals-mcp (or pip install lantern-works-deals-mcp, then lantern-works-deals-mcp).

Claude Code

claude mcp add --transport http lantern-works-gpu-prices "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-claude-code"

or local stdio:

claude mcp add lantern-works-deals -- uvx lantern-works-deals-mcp

Claude Desktop: claude_desktop_config.json (Settings → Developer → Edit Config). Or add the hosted URL under Settings → Connectors → Add custom connector: https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-claude-desktop

{ "mcpServers": { "lantern-works-deals": { "command": "uvx", "args": ["lantern-works-deals-mcp"] } } }

Cursor: ~/.cursor/mcp.json or .cursor/mcp.json (or use the button above)

{ "mcpServers": { "lantern-works-gpu-prices": { "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-cursor" } } }

VS Code (GitHub Copilot agent mode): .vscode/mcp.json

{ "servers": { "lantern-works-gpu-prices": { "type": "http", "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-vscode" } } }

Windsurf (now Devin Desktop): ~/.config/devin/mcp_config.json (older Windsurf builds: ~/.codeium/windsurf/mcp_config.json)

{ "mcpServers": { "lantern-works-gpu-prices": { "serverUrl": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-windsurf" } } }

Cline: cline_mcp_settings.json (MCP Servers → Configure)

{ "mcpServers": { "lantern-works-gpu-prices": { "type": "streamableHttp", "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-cline" } } }

OpenAI Codex CLI

codex mcp add lantern-works-deals -- uvx lantern-works-deals-mcp

Any other MCP client: stdio uvx lantern-works-deals-mcp, or Streamable HTTP https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme-other. More clients: https://thelanternworks.com/install/?ref=readme

Get your first quote — no installation or API key

Python 3.10+, standard library only. Read the example, then download and run it:

curl --fail --location https://raw.githubusercontent.com/connormatthewdouglas/agent-work-stack-deals/main/examples/first_quote.py --output first_quote.py

python3 first_quote.py --gpu 'H100 SXM' --hours 100 --ref readme

This calls the public hosted MCP: three on-demand rates checked within 24 hours, then a 100-hour, one-GPU compute estimate with sources, assumptions, missing costs and a receipt. It creates no purchase or watch. Use --qa for internal tests.

Client setup · Quickstart · Agent manifest · Small per-model JSON feeds · Add this to your README or dataset

Contact: lanternworks@agentmail.to

MCP server (v0.6.5, read-only, stdio)

Free, read-only, no API key. Package lantern-works-deals-mcp on PyPI; MCP Registry name io.github.connormatthewdouglas/lantern-works-deals. Built on the official Python MCP SDK.

Tool counts: 9 in the local package (stdio, below); 13 on the hosted endpoint (the same 9 plus create_watch_key, watch_price, list_watches, delete_watch).

The full tool contracts, eligibility and stale-price rules, hosted endpoint, alert delivery, throughput data, and the feed contract and deploy gate are in docs/CONTRACT.md. Arguments, errors, data sources and tests: mcp_server/README.md.

Tools (9, read-only)

ToolWhat it does
compare_gpu_pricesHourly rental prices for a GPU model across tracked providers, cheapest first. When a result includes availability_rate_7d, window_days is the planned window and observed_hours is the actual coverage (coverage_note when coverage is shorter). The output also carries file-level availability_window_summary (no-window counts by reason, plus when current windows began) and content_build_id.
get_price_changesGPU price moves among tracked providers, newest first.
optimize_stackCheapest tracked plan per usage line, with sources.
optimize_agent_stackCheapest cited option per component from a plain-text agent description.
estimate_job_costCost of one GPU job among tracked providers, cheapest first.
rebuild_quoteReopen a past quote and revalidate it against today's feed.
search_dealsSearch the deals feed by text, category, offer type, price and tags.
compare_dealsCompare 2-5 deals by id, best customer value first.
get_dealReturn the full public record for one deal id.

Keywords: MCP server, Model Context Protocol, GPU prices, cloud GPU pricing, GPU rental price comparison, H100 / H200 / A100 / L40S / RTX 4090 / RTX 5090 hourly price, GPU cost estimate, price history, AI infrastructure costs, Claude, Cursor, VS Code Copilot, Windsurf, Cline.

Quickstart: ask for compare_gpu_prices(gpu="H100"), then the next day call get_price_changes(since=" ") to see what moved. The feed rebuilds once a day (about 10:23 UTC). Every price shows its own checked_at/verified_at, and compare_gpu_prices and optimize_agent_stack return data_checked_at and next_refresh_utc.

Run locally / Docker / privacy

Docker: docker build -t lantern-works-deals-mcp . && docker run -i --rm lantern-works-deals-mcp (the root Dockerfile installs the pinned PyPI release and runs the stdio server). Without uv: pip install lantern-works-deals-mcp, then use "command": "lantern-works-deals-mcp". Other clients: https://thelanternworks.com/install/?ref=readme · Skill: npx skills add connormatthewdouglas/agent-work-stack-deals.

Telemetry is off by default. LANTERN_TELEMETRY=1 opts in to an anonymous daily count of tool calls: tool name, version, day and count only. No arguments, IDs or IPs are sent or stored. See PRIVACY.md.

Hosted endpoint (no install): https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=readme. Privacy and caller-count detail: docs/CONTRACT.md, PRIVACY.md and /privacy/.

Demo (live data, 2026-10-28): the MCP server answers "cheapest H100 for 100 hours?". It shows 100-hour totals for the cheapest, next and most expensive tracked rates, each with its source and check time, and labels referral links. Recording: docs/demo/cheapest-h100-100h.cast · script: docs/demo/demo.py.

Framework examples: LangGraph (cheapest H100), CrewAI and OpenAI Agents SDK (cheapest GPU for a described job), Stack optimizer (describe your agent, get the cheapest cited stack via optimize_agent_stack), GPU price watcher (what moved since a date via get_price_changes, cron-ready), GPU price monitor (price-drop alerts from the history API). All examples: examples/. Some tool results include referral links (affiliate: true).

Report a wrong price

See a price that doesn't match the vendor's page, or an offer you can't rent? Open a wrong-price report. Agents can prefill it from a feed row; see docs/REPORT-WRONG-PRICE.md.

License

  • Code: MIT, see LICENSE.
  • Field reference for canonical_model, form_factor, availability_rate_7d (window_days = planned window, observed_hours = actual coverage), file

只显示了开头部分;其余内容请在仓库中阅读