LPG Connector MCP Server

LPG Connector MCP Server

Enables Claude to query live LPG price and stock data, find nearest stations, view market trends, and submit crowdsourced price reports via MCP tools.

Category
访问服务器

README

LPG Connector — MCP Server

A remote MCP server that exposes live LPG price/stock data to Claude. Backed by in-memory mock data for now; built to swap to MongoDB with no changes to the tool logic.

Tools

Tool What it does
get_lpg_price(region?) Latest price/kg + stock per station in a region (omit region for all)
find_nearest_station(lat, lng, limit?) Nearest stations to a coordinate, with distance + latest price
get_market_trends(region, days?) Daily average price trend over the last N days
report_price(stationId, pricePerKg, stock, reporter?) Submit a crowdsourced price/stock report

stock is one of in_stock | low | out_of_stock.

Run locally

npm install
npm run dev        # tsx watch, http://localhost:3000/mcp

Health check: GET http://localhost:3000/health

Quick smoke test (list tools):

curl -s -X POST http://localhost:3000/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

Build for production

npm run build      # -> dist/
npm start          # node dist/index.js

Project layout

src/
  index.ts              Express + streamable HTTP transport (the /mcp endpoint)
  server.ts             MCP server + the 4 tool definitions
  store/
    types.ts            Domain types (Station, PriceReport, ...)
    DataStore.ts        Interface every store implements
    InMemoryStore.ts    JSON-seeded implementation (current)
  data/seed.json        Mock stations + price history

Swapping to MongoDB later

The tools only ever talk to the DataStore interface, so the migration is localized:

  1. npm install mongodb
  2. Create src/store/MongoStore.ts implementing DataStore (same method signatures as InMemoryStore). Map stations and priceReports to two collections.
  3. In src/index.ts, change one line:
    // const store = new InMemoryStore();
    const store = new MongoStore(process.env.MONGODB_URI!);
    

Nothing in server.ts changes. Seed the collections from data/seed.json once for a matching demo dataset.

Deploy (for the Claude custom connector)

Claude's cloud connects to this server over the public internet — a localhost URL won't work for claude.ai. This repo is set up for Render.

Deploy to Render

Option A — Blueprint (uses render.yaml, one click):

  1. Push this project to a GitHub repo.
  2. In Render: New → Blueprint, pick the repo. It reads render.yaml (build npm install && npm run build, start npm start, health check /health).
  3. Deploy. You'll get a URL like https://cylindr.onrender.com.

Option B — Manual web service:

  1. New → Web Service, connect the repo, set Root Directory to zserver.
  2. Build command: npm install && npm run build
  3. Start command: npm start
  4. Health check path: /health

After it's live

  • Confirm health: open https://<your-app>.onrender.com/health → {"status":"ok"}
  • Add to Claude: Settings → Connectors → Add custom connector, paste https://<your-app>.onrender.com/mcp, then enable it in a chat via the + menu.

Free-tier note: Render's free web services sleep after ~15 min idle and take ~30–60s to wake on the next request. Before your live demo, hit /health once to wake it so the first judge query isn't slow. Also: in-memory data is per-process, so a restart (or wake from sleep) resets to the seed and any report_price submissions are lost. The MongoDB swap removes both concerns.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选