Argentina Price Index

io.github.oscarlopez-gif由 GitHub 帳號 oscarlopez-gif 發布v0.1.0更新於 Oct 24, 2026

Daily Argentina food & beverage price index, source-cited from public retailer prices.

發布方自己的服務:PriceWin

已驗證Streamable HTTP可網頁執行金融資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,提供阿根廷食品與飲料每日價格指數,可免費取得最新值,完整序列需付費。

可以做什麼
  • 讀取食品與飲料指數的最新數值與 30 天變動率,可選 Jevons、Carli 或截尾估計方法
  • 比較同一底層資料在三種估計方法下的最新指數值
  • 取得完整的每日指數時間序列,可依乳製品、烘焙、生鮮、肉類、糧油、飲料等子類篩選
適用情境
適合試驗面向 AI 代理的價格指數介面或按次付費(x402 風格)流程,或示範通膨類資料取得。若需要真實的阿根廷價格資料則不適合。
執行需求
遠端 streamable HTTP 端點;未宣告任何套件、帳號、API 金鑰或環境變數。付費序列呼叫需在請求中附帶付款參數;README 的在本機執行需要 Node 18+ 與 Cloudflare 帳號。
安裝前請注意
README 明確說明資料為合成的佔位資料,不應視為真實的阿根廷價格。付款僅為共享密鑰 HMAC 模擬驗證,並非鏈上結算,且無重放保護;付費序列標價 0.02 美元。README 亦指出此端點不支援工作階段與身分驗證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Argentina Price Index,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.oscarlopez-gif%2Fargentina-price-index/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "argentina-price-index": {
      "type": "http",
      "url": "https://api.oscar-lopez.com/mcp"
    }
  }
}

README

Paid Door — Argentina food & beverage price index (Cloudflare sandbox)

A minimal, working test of the video's core mechanic: one agent request becomes a paid transaction at the edge. A Cloudflare Worker serves a live-computed price index from D1, gated by an x402-style 402 → pay → retry → data loop. Payment is mocked (shared-secret HMAC) so the whole loop runs with zero wallet setup; swapping in real x402 is a localized change.

Data is synthetic. seed/observations.sql is generated placeholder data so the demo runs before a real scraper exists. Do not treat the numbers as real Argentine prices.

What's here

paid-door-index/├─ wrangler.jsonc         # Worker + D1 binding + sandbox vars├─ schema.sql            # price_observations + methodology (+ future index_series cache)├─ seed/│  ├─ generate.mjs       # deterministic synthetic data generator (60 SKUs x 30 days)│  └─ observations.sql   # generated seed (1,800 rows)├─ src/index.ts          # Worker: routes + live index math + mock x402 gate├─ agent/test-agent.mjs  # the paying "buyer": request → 402 → pay → retry → data└─ README.md

Endpoints

EndpointTierReturns
GET /v1/headline?country=AR&category=food_beveragesfreelatest index value + monthly rate (the teaser)
GET /v1/index?country=AR&category=food_beveragespaid ($0.02)full daily series
GET /v1/latest?country=AR&category=food_beveragespaid ($0.02)latest reading + methodology
POST /mcp—MCP JSON-RPC: initialize, tools/list, tools/call

MCP interface (what agents actually call)

The Worker also speaks MCP over HTTP at /mcp, exposing two tools:

  • get_ar_food_headline (free) — latest value + 30-day rate
  • get_ar_food_price_index (paid, $0.02 mock-x402) — full daily series; call once with no _payment to receive a challenge, then retry with arguments._payment = {nonce, resource, amount, signature}

Test the full agent flow (with npm run dev running):

bash
npm run agent:mcp     # initialize → tools/list → free call → paid call (challenge → pay → data)

Production note: /mcp here is a minimal JSON request/response subset of the Streamable HTTP transport (no SSE/sessions/auth). For a real deployment use the official MCP SDK or Cloudflare's agents McpAgent, and replace the mock HMAC with a real x402 facilitator.

Index math (methodology_version = v0-simple-avg): index = 100 × mean(price_t / price_base) over in-stock SKUs, base = first day in the window. Upgrade path baked into the schema: geometric mean within category + Laspeyres across categories.

Run it locally

Prereqs: Node 18+ and a Cloudflare account (npx wrangler login).

bash
cd paid-door-indexnpm install
# 1. Create the D1 database, then paste the printed database_id into wrangler.jsoncnpm run db:create
# 2. Load schema + seed into LOCAL D1npm run schema:localnpm run seed:gen        # (optional) regenerate observations.sqlnpm run seed:local
# 3. Start the Workernpm run dev             # serves http://127.0.0.1:8787
# 4. In a second terminal, run the paying agentnpm run agent

Expected agent output: the free headline, then a 402 with a price challenge, then a 200 with the full series and a PAYMENT-RESPONSE settlement header — one request turned into a transaction.

Deploy to your account

bash
npm run schema:remotenpm run seed:remotenpm run deploy# then point the agent at the deployed URL:BASE=https://paid-door-index.<your-subdomain>.workers.dev npm run agent

Watch live logs with npx wrangler tail.

Sandbox → real (later)

  1. Real data: replace seed/generate.mjs with a scheduled Worker that scrapes 1–2 Argentine online grocers daily into price_observations.
  2. Real payment: replace the HMAC mock in src/index.ts (verifyPayment / challenge) with a real x402 facilitator (POST /verify, POST /settle) per Cloudflare's Agents x402 docs.
  3. Move the secret: npx wrangler secret put MOCK_PAYMENT_SECRET instead of the plain var.
  4. Expose as MCP so any AI agent (including this assistant) can call get_index directly.
  5. Materialize index_series as a nightly cache once query volume grows.

Notes / caveats

  • Mock payment proves knowledge of a shared secret — it is not cryptographic on-chain settlement. It exists only to exercise the request/response shape.
  • No replay protection in the sandbox (any valid signature can be reused). Real x402 settlement handles this.
  • The synthetic monthly rate is intentionally noisy; single-endpoint inflation reads jump around, which is itself a good classroom point.

來源:README.md,提交 a65037e

工具

3

get_ar_food_headline

Free: latest Argentina food & beverage price index value + 30-day rate, source-cited and updated daily. Optional method: jevons (default, recommended), carli, or trimmed. For the full daily series use get_ar_food_price_index.

輸入參數methodcategory

get_ar_food_methods

Free: methodology comparison — the latest Argentina food & beverage index under every estimator (Jevons geometric mean, Carli arithmetic mean, trimmed mean), all computed from the same underlying data. Zero cost.

輸入參數category

get_ar_food_price_index

Returns the full daily Argentina food & beverage price index time series (base=100). Source-cited from public retailer prices, updated daily, methodology published. Options: method (jevons/carli/trimmed), subcat (dairy/bakery/produce/meat/pantry/beverages) for a subcategory sub-index. Free during the public preview; metered x402 access ($0.02/call) is coming. Free headline via get_ar_food_headline.

輸入參數methodsubcatcategory

版本歷史

1
  1. v0.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Price 整合