mcd-coupon-strategist skill
Skill compares McDonald's China meals and coupons to calculate the cost and eligible discounts at a selected restaurant
- 992 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- The connection exposes purchase history and account information to the agent
- Claiming coupons through MCP tools changes account data
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/mcd-coupon-strategistDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The connection exposes purchase history and account information to the agent
- Claiming coupons through MCP tools changes account data
This is third-party code. Review the repository files before installing.
What it does
The mcd-coupon-strategist skill helps an agent compare McDonald's China orders. It first identifies the restaurant and fulfillment method, then retrieves menus and coupons through MCP and prices candidate combinations. A Python module filters candidates by requested contents and budget. The agent presents a recommendation, alternatives and an explanation of the price difference. The skill separately checks whether the discount covers purchases added to meet the coupon threshold. Another workflow examines order history and remaining coupons, relating expiry dates to likely ordering opportunities. The collection also checks loyalty points and a campaign calendar.
Who it is for. For McDonald's China customers and agent-workflow developers who need order comparisons based on a particular restaurant's data.
Good fit when
- Compare a set meal with the same items bought separately using eligible coupons
- Check whether additional purchases to reach a coupon threshold are worthwhile
- Analyze past spending while separating paid purchases, refunds and zero-value orders
- Check which soon-expiring offers can still fit planned ordering opportunities
Not a fit when
- You need Russian restaurant prices or another chain's coupons
- You need nutrition or medical dietary recommendations
- You expect a globally lowest price without checking current menus and conditions
Example request
For my selected McDonald's China restaurant, compare a set meal with its items purchased separately. Include delivery and explain coupon eligibility. Do not place an order or claim coupons without my approval.Limitations
Live data requires a personal McDonald’s China MCP token and a compatible client; order history, addresses and coupons belong to the account. The skill is unofficial, and the external operator determines available functions and responses. Calculations depend on menu coverage and restaurant rules; missing prices and unknown expiry dates must stay unconfirmed. Partial refunds can inflate spending totals when the API omits the refunded amount; check disputed purchases against account history.
How to disable. Remove the skill directory or stop attaching its instructions. Remove the MCP connection and revoke its token to end account access. Clean up saved purchase-history exports separately.
FAQ
Can I try it without signing into McDonald's?
Yes. Run `python demo.py` from the checkout root. It uses responses stored in `fixtures/` without requesting live data. The amounts belong to that demonstration snapshot.
Which server is needed for live data?
McDonald's China MCP at https://mcp.mcd.cn. Obtain a token from your own account at open.mcd.cn and supply it through the client's authorization header. The skill repository does not include your account access.
How is a candidate order priced?
Each candidate goes to `calculate-price`. Its response provides the restaurant-specific price and discount. Include delivery and the actual contents of set meals in the comparison.
Can the agent claim an account coupon?
Yes, through the external `auto-bind-coupons` tool. That changes account state. Instructions require user approval, while the MCP client enforces tool permissions.
Can points be converted to a fixed cash discount?
No. Points have no fixed cash conversion rate. The skill shows eligible rewards, their point costs and redemption dates. Cash value depends on the specific offer.
What license and dependencies apply to the scripts?
MIT and Python 3.8 or later. No third-party Python libraries are required.
Discussion
No questions or reviews yet.
Related
SkillsAn agent skill that goes through McDonald's China menus and coupons and picks the lowest-priced order
With mcd-cn-assistant, an agent compares McDonald’s China menus and coupons and prices a group order before purchase.
Picks a complete McDonald's China order for your budget and taste at official prices and returns a ready order card
McButler (mcd-self-butler)
mcd-self-butler
McButler works out calories and the full cost of an order, including travel and queue time, from the McDonald's China MCP
A skill for the McDonald's China MCP: claims coupons, checks per restaurant which one redeems and computes the discounted price.
A skill on the McDonald's China MCP: turns a budget and wishes into up to three menus with official prices, leftover budget and coupon terms
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| mcd-coupon-strategist (this card) | no | 992 | ||
| MCD Saver Strategist | no | 1,543 | optimizes order combinations and per-person prices; this skill also examines purchase history and coupon timing | |
| mcd-cn-assistant | no | API key | 379 | With mcd-cn-assistant, an agent compares McDonald’s China menus and coupons and prices a group order before purchase. |
README in short
An adapter normalizes amounts from different MCP responses to one monetary unit before calculation. The collection includes checks for individual modules.
README badge
Original SKILL.md
--- name: mcd-coupon-strategist description: 麦麦省钱助手。基于麦当劳中国 MCP 的实时菜单、门店优惠券与计价能力，计算当前门店下最省钱的点餐方案（附省钱归因与凑单陷阱提示），并审计历史订单与券存量、量化即将过期券的「沉默成本」、对券包做净价值体检（哪些券该用、哪些别用）、在有限点单机会下安排用券、发现麦麦省里还没领取的券（哪些值得领）、体检积分账户（余额、已过期、能换什么、够不够），以及把活动时间线与券的有效期对起来（「等活动再买」等不等得起）。当用户提到「麦当劳怎么点最便宜」「麦麦省钱」「帮我算一下这单划不划算」「用哪张券合适」「预算多少能吃什么」「我最近在麦当劳花了多少」「有没有券快过期了」「这些券该怎么用」「有什么券可以领」「我有多少积分」「积分能换什么」「最近有什么活动」「现在买还是等等」时使用本 Skill。 agent_created: true --- # 麦麦省钱助手 ## 角色 扮演严谨的点餐成本优化助手。唯一目标不是让用户多买，而是**在满足用餐需求的前提下，把实付金额压到最低**。 本 Skill 提供两种视角，对应两条独立链路： | 视角 | 回答的问题 | 链路 | |---|---|---| | 短期 | 这一单怎么点最省 | 链路 A | | 长期 | 用户正在白扔多少钱 | 链路 B | ## 何时使用 **触发（任一命中即使用）** - 单次省钱：「麦当劳怎么点最便宜」「帮我算一下这单划不划算」「用哪张券合适」「预算 40 能吃什么」 - 消费审计：「我最近在麦当劳花了多少」「有没有券快过期了」「我是不是买贵了」 **不触发** - 门店营业时间、投诉、会员卡规则等非成本问题 —— 正常回答即可 - 纯营养 / 热量 / 健康咨询 —— **本 Skill 不做这类建议**（见铁律 7），如实说明它只解决成本问题 **主动性要求**：即使用户只是随口聊到点餐，只要已建立门店上下文，**主动提醒「你还有 N 张券快过期」**。这是本 Skill 最有价值的输出时刻。 ## 铁律