McDonald's Coupon Strategist
Price the cheapest McDonald's China order at your store, and audit the coupons and points quietly expiring on your account.
- What
- Price the cheapest McDonald's China order at your store, and audit the coupons and points quietly expiring on your account.
- Cost
- Free
- Needs
- Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
A cost optimizer and account auditor for McDonald's China, built on the live menu, store coupons and pricing of the McDonald's China MCP. Chain A prices the cheapest order at one store (combos versus single items, best coupon, filler trap warnings, savings explained). Chain B audits what you are quietly losing: order history profile, coupons about to expire and their silent cost, a net value check of your whole coupon wallet, a redemption schedule for your limited ordering chances, claimable coupons you have not picked up yet, a points account check (balance, expiry, what you can actually still redeem), and the campaign calendar lined up against coupon expiry dates. It never places an order: the only write on your account is claiming coupons with auto-bind-coupons, and only after it lists them and you explicitly agree. Fully offline demo and tests run on the bundled fixtures with no token.
Version:
Install
Copy the install package below, then paste it into Muse📌 Pinned version: commit e391fd0The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
- It can run commands on your Muse’s computer.
- It can download and install software packages.
What the scan found — excerpts from the install prompt
- runs commands — git clone https://github.com/Ayzzz123/mcd-coupon-strategist.git · cd mcd-coupon-strategist · python demo.py
- installs packages — git clone https://github.com/Ayzzz123/mcd-coupon-strategist.git · # 本项目零第三方依赖,无需 pip install -- 八套测试与 demo 均只依赖标准库
Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites: Account and token required before any real use: a McDonald's China MCP token. The listing is free, and activating the token is described upstream as free. Get the token yourself, in person, because it needs mobile phone number verification: go to https://open.mcd.cn/mcp , sign in with your mobile phone number, open the console at the top right, click Activate, agree to the service agreement, and copy the token. Then configure the McDonald's China MCP server: name mcd-mcp, type streamablehttp, URL https://mcp.mcd.cn , header Authorization: Bearer <your token>, or set the MCD_MCP_TOKEN environment variable where the skill reads it that way. Keep the token only in your own private client configuration or environment: never commit it, never share it, and never paste it into a shared chat. Upstream states a limit of 600 requests per minute per token (429 above that). The repo ships its own step by step token guide at docs/TOKEN_GUIDE.md, which describes exactly the flow above (phone verification login, console, Activate, agree, one click copy, then paste the config into your MCP client and enable and trust the mcd-mcp connector). You also need Python 3.8 or later (zero third party dependencies, standard library only). The bundled demo and fixtures run fully offline with no token; every real menu, coupon, order history or points figure needs the token. Install "McDonald's Coupon Strategist" for me. It prices the cheapest order at your store from live MCP data, and audits your order history, expiring coupons, points and campaign dates. It never orders for you. Repository: https://github.com/Ayzzz123/mcd-coupon-strategist (the skill is the whole repository at the pinned commit, SKILL.md at its root: 44 files, listed in the fingerprints below) Pinned version: install the code at commit e391fd00ad7322ddddd5d15d88c403c5459f0f5d exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Ayzzz123/mcd-coupon-strategist into a temporary folder, check out commit e391fd00ad7322ddddd5d15d88c403c5459f0f5d, and copy the whole repository folder from that checkout, excluding the .git folder. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-18: [FINGERPRINTS] - .env.example: SHA-256 95703553d39ef01423210ce924b0374cc3ff38fb34bd66c1fa8d62d430ff4231 - .github/workflows/tests.yml: SHA-256 9feef7ccd9cd4c236a143002c1c5e1176fda3730d7b8ca94cc25d1c9cc19beb0 - .gitignore: SHA-256 c087fb7e0e26ca829c904549bf831da54d7f9c64653db7d501132e176f7d9053 - CONTEST_DECLARATION.md: SHA-256 cd28101bcb29cc8fb24b372fe91ce6b42c4a1487a54e01f7ade0c8c6a84241b7 - LICENSE: SHA-256 2f249563a9bf87d544fad5b633a6b869c0c645050cee955252f07c3cc2e11f53 - MCP_INTEGRATION.md: SHA-256 e5d632412f91f68e266bae7a3b1fb9bc8c70018e725e5a58503cd7a48c780b1a - README.md: SHA-256 f0e5e478c7452ee6eababb7746f63d9ef65518e6bc43b920a9ba6ae12f7e9a04 - SKILL.md: SHA-256 611bfe29e4d9fcf65655822fc81202aa8e83a9cb55a9d7460534d7186bf4356a - assets/architecture.svg: SHA-256 18ab52fc686451c1ec50010ae5e29281cd42d398469b10bdc84c3c41e7a004f1 - assets/banner.svg: SHA-256 ed8d5247f4656105b1db3b9e7cbf7869697d135ddf61e6595d5c7172f5151321 - assets/demo-dual-view.svg: SHA-256 ca81d59361abec15d27a6c3655ca2cd8aed552faa1e303172de64ce1a325ab64 - assets/social-preview.png: SHA-256 3751d4b92a7da6c06160fe4c0ea9595e4940bab2e0ef07351f71eafebc644ced - demo.py: SHA-256 520c999c772b4bdd27c79adca608e1f0305e053ede38ec88fcf005956e434622 - docs/SUBMIT_CHECKLIST.md: SHA-256 9a37d40a2d2e6407be58f7ef1523b5260131065acf3b796c82de9793aae4d668 - docs/TOKEN_GUIDE.md: SHA-256 95b2f4a702a09fc91e9a0eae95f5d12c655e1d76c3e53a446d8d76b825efd902 - fixtures/README.md: SHA-256 aeb7050282684c47b23f87f9895bf5c941ef06cf49b368037a35dc84e4ca8894 - fixtures/available_coupons.json: SHA-256 0b19f476e3b7b935ac3b9586732cdc901e93eca188aa960c7114493cf33cb2a3 - fixtures/campaign_calendar.md: SHA-256 0e1337b97165d3e5ee1e957e3735189241092d7ce75f1a6af9fdbd128bb25c53 - fixtures/coupon_probe.json: SHA-256 a3b297078f462477acb3717498470cabd208180468281c9ec41ff2ee2e971ff0 - fixtures/coupons.json: SHA-256 7bbf320167775f10ca788f835e3980a98f6e34f94b444bb749d4501570f119c6 - fixtures/meal_detail.json: SHA-256 fb1071d5b3110d133da1ec82e10a86e9ae68959236f85540fbd05ba41bf3bff9 - fixtures/menu.json: SHA-256 e1645b7230a4015466870d99553f655f40530b91748c6ed31f0dc3bcb3a5160e - fixtures/my_coupons.md: SHA-256 037df00a34078f67b28774a4efbe4f35280d5d17c4f68afb89d994b6ffc906f1 - fixtures/orders.json: SHA-256 7237599aaef039dad6adb9f872568bbaf040341bd281f90ab56672e85dea823c - fixtures/points_account.json: SHA-256 8909c46868e21d84cebd8a27bdeefbb8d7ec5a05d47327089baaeac1f12a8e98 - fixtures/points_products.json: SHA-256 7e49fb94ed07c6b510633a813cbe2dcc06c993b70d00310c22773605b63837e0 - fixtures/prices.json: SHA-256 03bc1849a9313f6fcadc39e8c044a8a36387978e090913a4993c2d01d1614efa - mcp-config.example.json: SHA-256 7644e429708a6aa8ceb09505dcd0fc9a092b3608e974767360f4c158cb1047dd - scripts/style_check.py: SHA-256 e363b36759280893e1a3cd885c2e3a6bdcfc739c1e65d468d4aa679f8ec291e6 - src/auditor.py: SHA-256 255c934e4d74fca781fbc2b12c1a27eb6e955152e61ed6cb0f90f91f13635382 - src/campaign.py: SHA-256 ee761f6f315d67180e5eb75d15e3e91f4e7527367cc49f422485516dec024827 - src/mcd_adapter.py: SHA-256 9cc5362cab7d611b9f407f2fab6c109e8346bccd6a2e315b063ea0e1dcbf3e73 - src/planner.py: SHA-256 62dc35e0da5bebc50ace541450719c95f6f78305421dcb28480b38f9dbca3d23 - src/points.py: SHA-256 ae9f90e62339db875bafa19548ed58bca41086c3eb3cd9ffc64156b6d6f916c6 - src/saver.py: SHA-256 2e31e37d3616da8d8758eb30813e37f837a38be2f4519d36ea063fbb08699bd7 - src/test_adapter.py: SHA-256 878d1d196ed1e21ca3a624edaa88ca79a44dfce3188cfe60149c01c414960a98 - src/test_auditor.py: SHA-256 d897110685dd7a4553ee825697645433eafa75e060cb2047117169ab4eff5ad2 - src/test_campaign.py: SHA-256 485b6dba93793102a64be24dd408b74a67cfcb88adfecdecd3997b1a9a5e21c2 - src/test_claimable.py: SHA-256 1c4c64c324ae4496dcd813145daf64fd4654a60017a21c4626f58173ae4790e9 - src/test_order_adapter.py: SHA-256 bfdefd62c5c17e5715791ae217b58a2c3a50bf9b58e5d08716dcc24c9abd9697 - src/test_planner.py: SHA-256 e70670ff75a2e1fcbc317521e8c42b4c0b00fda8ab7e3ee14b648b748f24da00 - src/test_points.py: SHA-256 4e4f0570ce39f2d02759e6fa9d4025a9c69e1820841ff31ceeb209cee5e276f4 - src/test_saver.py: SHA-256 00971cffd1ff49826e23b4c9569b0041c4cc5fcf8b263b9d2620500aea25f8ab - workbuddy.md: SHA-256 6336cee09f23b37986d711dabf4dd370189ea9e997c749c18abf1561d245829f If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full (and every other file in the folder) and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill is the whole repository at the pinned commit (SKILL.md at the root): the business logic lives in src/ (mcd_adapter.py, saver.py, auditor.py, planner.py, points.py, campaign.py, plus their test files), with demo.py, fixtures/ (sample menus, coupons, orders and points used offline), docs/ (including docs/TOKEN_GUIDE.md), MCP_INTEGRATION.md, README.md, workbuddy.md, mcp-config.example.json, .env.example, assets/ and scripts/style_check.py. No code in the repo makes HTTP calls itself: the Python modules only transform MCP responses that your agent host fetches through its own MCP connector, and the demo and tests run on the local fixtures. - At use time, your agent sends MCP tool calls to https://mcp.mcd.cn (Streamable HTTP, Authorization: Bearer token) with these arguments: for one order, the dining mode and either a delivery address identifier from your account (delivery-query-addresses then delivery-query-stores) or a store lookup (query-nearby-stores with beType and searchType), then storeCode, orderType and beType with query-meals, query-store-coupons and query-my-coupons, query-meal-detail for combo structure, and calculate-price with items as productCode and quantity pairs, sometimes with a couponId and couponCode to measure a coupon's real value. For the audit, it calls order-list with no arguments (your full order history comes back), query-my-coupons, now-time-info, query-my-account with no arguments and mall-points-products (your points balance and expiry come back), mall-product-detail, available-coupons and campaign-calendar. So the server receives your token, store, items and coupon identifiers, and returns your order history, coupons and points data to your machine, where the local Python modules do the math. Nothing is sent to any other host by the skill code. - This skill places no order and makes no payment: no create-order call appears in its SKILL.md, its src/ modules or its MCP_INTEGRATION.md. Its only account write is auto-bind-coupons, claiming coupons to your account, and its own iron rules require it to first tell you which coupons can be claimed and whether they are worth it, and to run it only after your explicit agreement. Prices are never guessed: every amount must come from a calculate-price response, in cents converted to yuan by the adapter. - Nothing is sent anywhere during installation itself; the only download at install time is the repository from GitHub at the pinned commit. The listing and the token are free; you pay only for McDonald's food you order yourself through official channels, never through this skill. 3. When I say "yes, install", install it as a skill: copy the whole folder into the agent's skills directory, in a folder named "mcd-coupon-strategist", keeping every file listed in the fingerprints above. 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (for example: get the McDonald's China MCP token myself at https://open.mcd.cn/mcp with my mobile phone number if I do not have one, put it only in my own private MCP client configuration or environment variable and never paste it into a shared chat, install Python if it is missing, and set up the mcd-mcp connector to https://mcp.mcd.cn if it is not configured; using the skill is a separate step that only starts when I ask for it, and any order, coupon claim or booking happens only as disclosed above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.