How do I install the Mcdonalds MCP Order Lite skill?

Run npx skillmds@latest add dvcrn/mcdonalds-mcp-order-lite in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Mcdonalds MCP Order Lite safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Mcdonalds MCP Order Lite?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Mcdonalds MCP Order Lite free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Mcdonalds MCP Order Lite?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Mcdonalds MCP Order Lite by dvcrn — Agent Skill

Name: Mcdonalds MCP Order Lite
Rating: 4.5 (4 reviews)
Author: dvcrn

Mcdonalds MCP Order Lite

Place McDonald's China delivery orders through the official MCP server at https://mcp.mcd.cn using a Bearer MCP token over Streamable HTTP / JSON-RPC. Use when the user wants to browse McDonald's deliverable addresses, query store menu items, inspect meal details, calculate price, create a delivery order, query order status, or check McDonald's coupons/points. Also use when wiring this MCP into a client like Cursor, Cherry Studio, Trae, or another agent. This lite package intentionally contains no embedded token and only the core reusable files.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Use the official McDonald's China MCP toolchain, not scraped web APIs.

Core workflow

Identify the delivery address.
Call delivery-query-addresses first.
Pick the matching address record and carry forward addressId, storeCode, and beCode from the same record.
Call query-meals for that store.
If needed, call query-meal-detail for a chosen meal code.
Call calculate-price before ordering.
Show the user the real payable amount and wait for confirmation.
Call create-order only after confirmation.
Return the payH5Url to the user.
After the user says payment is complete, call query-order.

Important constraints

Use server URL https://mcp.mcd.cn.
Send Authorization: Bearer <TOKEN>.
MCP protocol version must be 2025-06-18 or earlier.
Prefer low request volume; the docs say 600 requests/minute/token.
Do not invent storeCode, beCode, or addressId.
For delivery ordering, always use values returned by delivery-query-addresses or delivery-create-address.
Always price-check with calculate-price before create-order.
query-meal-detail docs note that replacing default combo choices is not yet supported in current version.

Tool map

Delivery ordering

delivery-query-addresses: list saved deliverable addresses
delivery-create-address: add a new delivery address
query-store-coupons: coupons usable for the chosen store
query-meals: menu for the chosen store
query-meal-detail: inspect a meal / combo
calculate-price: final price check
create-order: create payable delivery order
query-order: query order status after creation/payment

Other useful tools

available-coupons: claimable coupons
auto-bind-coupons: one-click claim current coupons
query-my-coupons: coupon wallet
list-nutrition-foods: nutrition list
query-my-account: points account
mall-points-products, mall-product-detail, mall-create-order: points mall
campaign-calendar: marketing calendar
now-time-info: server time

Recommended user-facing flow

When the user says “帮我点麦当劳” or similar:

Confirm budget / preferred item if missing.
Resolve the delivery address from saved addresses first.
Find candidate items from query-meals.
Use calculate-price for one or a few concrete combinations.
Present the cheapest / best-fit options with real payable totals.
Only place the order after explicit confirmation.
After order creation, send the payment link.
After payment, query query-order instead of assuming success.

Files in this skill

Read references/api.md for the compact API cheat sheet and tested field names.
Use scripts/mcd_rpc.py for direct RPC calls to the remote MCP server when you need deterministic testing or CLI usage.
client.py contains a Python wrapper around the same remote MCP calls.
nlp_processor.py contains lightweight text parsing for order intent.
tools.py contains higher-level helper functions.

Packaging notes

Keep the skill folder lean. Do not add extra docs beyond what is needed for reuse. Remove transient files like __pycache__ before packaging.

---name: mcdonalds-mcp-order-litedescription: Place McDonald's China delivery orders through the official MCP server at https://mcp.mcd.cn using a Bearer MCP token over Streamable HTTP / JSON-RPC. Use when the user wants to browse McDonald's deliverable addresses, query store menu items, inspect meal details, calculate price, create a delivery order, query order status, or check McDonald's coupons/points. Also use when wiring this MCP into a client like Cursor, Cherry Studio, Trae, or another agent. This lite package intentionally contains no embedded token and only the core reusable files.---Use the official McDonald's China MCP toolchain, not scraped web APIs.## Core workflow1. Identify the delivery address.2. Call `delivery-query-addresses` first.3. Pick the matching address record and carry forward `addressId`, `storeCode`, and `beCode` from the same record.4. Call `query-meals` for that store.5. If needed, call `query-meal-detail` for a chosen meal code.6. Call `calculate-price` before ordering.7. Show the user the real payable amount and wait for confirmation.8. Call `create-order` only after confirmation.9. Return the `payH5Url` to the user.10. After the user says payment is complete, call `query-order`.## Important constraints- Use server URL `https://mcp.mcd.cn`.- Send `Authorization: Bearer <TOKEN>`.- MCP protocol version must be `2025-06-18` or earlier.- Prefer low request volume; the docs say 600 requests/minute/token.- Do not invent `storeCode`, `beCode`, or `addressId`.- For delivery ordering, always use values returned by `delivery-query-addresses` or `delivery-create-address`.- Always price-check with `calculate-price` before `create-order`.- `query-meal-detail` docs note that replacing default combo choices is not yet supported in current version.## Tool map### Delivery ordering- `delivery-query-addresses`: list saved deliverable addresses- `delivery-create-address`: add a new delivery address- `query-store-coupons`: coupons usable for the chosen store- `query-meals`: menu for the chosen store- `query-meal-detail`: inspect a meal / combo- `calculate-price`: final price check- `create-order`: create payable delivery order- `query-order`: query order status after creation/payment### Other useful tools- `available-coupons`: claimable coupons- `auto-bind-coupons`: one-click claim current coupons- `query-my-coupons`: coupon wallet- `list-nutrition-foods`: nutrition list- `query-my-account`: points account- `mall-points-products`, `mall-product-detail`, `mall-create-order`: points mall- `campaign-calendar`: marketing calendar- `now-time-info`: server time## Recommended user-facing flowWhen the user says “帮我点麦当劳” or similar:- Confirm budget / preferred item if missing.- Resolve the delivery address from saved addresses first.- Find candidate items from `query-meals`.- Use `calculate-price` for one or a few concrete combinations.- Present the cheapest / best-fit options with real payable totals.- Only place the order after explicit confirmation.- After order creation, send the payment link.- After payment, query `query-order` instead of assuming success.## Files in this skill- Read `references/api.md` for the compact API cheat sheet and tested field names.- Use `scripts/mcd_rpc.py` for direct RPC calls to the remote MCP server when you need deterministic testing or CLI usage.- `client.py` contains a Python wrapper around the same remote MCP calls.- `nlp_processor.py` contains lightweight text parsing for order intent.- `tools.py` contains higher-level helper functions.## Packaging notesKeep the skill folder lean.Do not add extra docs beyond what is needed for reuse.Remove transient files like `__pycache__` before packaging.

Frequently asked questions