NorthCinder
NorthCinder is an MCP server that enables AI agents to compare products against a brief, rank them with explanations, and support approved checkout, all while running locally with privacy controls.
README
NorthCinder
Make your shopping agent compare, explain, and ask before buying.
NorthCinder helps your AI agent search for products, compare them against your brief, and show why one option ranks above another. Seller payment and affiliate data never improve a result's position.
NorthCinder runs on your computer alongside the AI app you already use. There is no NorthCinder account or cloud service.
Get started
You need Node.js 20 or later and an AI app that supports MCP. MCP is the standard the app uses to connect to tools running on your computer.
npx northcinder init
The initializer walks you through setup and prints the configuration to add to your AI app. Once connected, try a specific brief:
Find black wool running shoes under $130. Compare price, delivery, fit, and merchant trust. Tell me why the winner ranked first and which options were ruled out.
What you get
- A ranked shortlist based on the requirements and preferences in your brief.
- Reasons for every recommendation, including tradeoffs and missing information.
- Sponsored offers labeled and placed below organic results.
- Merchant trust evidence and an honest report of which stores were searched.
- A local history you can review, correct, and use to improve later searches.
- A separate approval step before any automated checkout.
How NorthCinder works
- You tell your agent what you want, what matters, and your budget.
- NorthCinder collects candidates from the direct store connections you configured. Your agent can also pass product details from browser tools it already controls.
- NorthCinder checks the candidates, ranks them against your brief, and returns a shortlist with reasons and coverage gaps.
- If you choose to buy, NorthCinder asks you to approve the exact item, quantity, and spending limit.
Results reported from a browser are clearly marked as agent-observed. You can compare them and open the product page, but NorthCinder will not use them for automated checkout or a background price watch until a direct store connection confirms the offer.
Store coverage
Store access varies because each platform has different rules. NorthCinder reports a store as unavailable or blocked when it cannot search it, rather than presenting partial coverage as a complete market search.
| Store | What works today |
|---|---|
| Shopify | Catalog search is available after additional Shopify setup. The older per-store connection is no longer current. |
| WooCommerce | Works with stores that expose WooCommerce's public Store API. |
| eBay | Native search requires approved eBay Buy API access. |
| Etsy | Native search requires approved Etsy app access. |
| Amazon | Read-only comparison can use a browser profile you control. It stops at challenges and does not check out. |
When a native store connection is unavailable, your agent may still compare permitted product pages with browser tools it already has. NorthCinder accepts only product facts needed for comparison. It does not take over the browser or ask for cookies, page contents, passwords, one-time codes, or your AI provider key.
Privacy and control
NorthCinder is software you run. The repository owner does not operate a NorthCinder service.
- Your AI provider key stays in your AI app. Store logins stay with you and the store.
- NorthCinder does not send your searches, settings, or local history to the repository owner.
- NorthCinder never accepts raw card details. Automated checkout can use a payment token created for the purchase, or NorthCinder can hand you a cart to finish in your own browser.
- Search is not permission to buy. Every automated checkout needs your approval for that purchase.
Learn more
- Why NorthCinder exists
- How ranking works
- How merchant trust works
- Privacy and software ownership
- Build from source or contribute
- Report a security issue
NorthCinder is open source under the MIT License.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。