← Back to Skills Marketplace
mcdonalds-mcp-order-lite
by
danielliao
· GitHub ↗
· v1.0.0
· MIT-0
311
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install mcdonalds-mcp-order-lite
Description
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 wh...
Usage Guidance
This skill implements McDonald's China MCP ordering and will contact https://mcp.mcd.cn using a Bearer token, but the registry metadata omits the required environment variables. Before installing: (1) treat MCD_MCP_TOKEN as a secret — only provide it if you trust the skill source; (2) verify where the package came from (there's no homepage/source URL); (3) consider running the code in a sandbox to confirm network behavior; (4) ensure your environment has required Python deps (requests and OpenClaw runtime) and decide how you'll securely store the token (platform secret store, not plaintext env if possible); (5) if you need higher assurance, ask the publisher to update metadata to declare required env vars and provide a source repo or signed release. If the publisher cannot justify the missing credential declaration or provide a trusted source, treat this package as untrusted.
Capability Analysis
Type: OpenClaw Skill
Name: mcdonalds-mcp-order-lite
Version: 1.0.0
The skill bundle is a legitimate integration for the McDonald's China MCP (Model Context Protocol) service, allowing an AI agent to browse menus and place delivery orders. The code (client.py, tools.py) implements standard API interactions using the requests library, and the instructions in SKILL.md explicitly mandate user confirmation of prices before order creation. No evidence of data exfiltration, unauthorized execution, or malicious prompt injection was found; sensitive credentials like the MCP token are handled via environment variables as expected for this architecture.
Capability Assessment
Purpose & Capability
The name, SKILL.md, and included files (client.py, scripts/mcd_rpc.py, tools.py, nlp_processor.py) consistently implement McDonald's China MCP ordering functionality against https://mcp.mcd.cn. The code provides menu, order creation, pricing, and intent parsing as advertised, so capabilities align with purpose.
Instruction Scope
Runtime instructions in SKILL.md describe the MCP JSON-RPC flow and the required steps (query addresses, calculate-price, create-order, etc.). The code follows that flow and only references network calls to the MCP server and user-provided data (addresses, items, location). There are no instructions to read unrelated system files or exfiltrate data to unknown endpoints.
Install Mechanism
There is no install spec (instruction-only from a packaging perspective), and no remote downloads — low install risk. However, the package includes Python code that depends on libraries (requests, urllib) and OpenClaw runtime APIs (openclaw.skill). Those runtime dependencies are not declared in the registry metadata; the skill will fail or behave unexpectedly if the runtime lacks required libs or the OpenClaw API.
Credentials
The registry metadata lists no required environment variables or primary credential, but client.py and scripts/mcd_rpc.py clearly read MCD_MCP_TOKEN (and optionally MCD_MCP_URL). SKILL.md explicitly instructs use of 'Authorization: Bearer <TOKEN>'. This mismatch is a material incoherence: the skill requires a sensitive token (Bearer token) to function, yet the package metadata does not declare or explain that. No other unrelated credentials are requested, but the omission makes it unclear how the token should be supplied/managed.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide config, and appears to only register tools via openclaw.skill.tool. Autonomous invocation is allowed (platform default) but not combined with other broad privileges. The skill does not write installers or run remote code downloads.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mcdonalds-mcp-order-lite - After installation, invoke the skill by name or use
/mcdonalds-mcp-order-lite - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of mcdonalds-mcp-order-lite for McDonald’s China delivery ordering via the official MCP server.
- Supports browsing deliverable addresses, store menus, meal details, coupons, price calculation, and order creation/status.
- Uses secure Bearer MCP token authentication; no embedded tokens included.
- Designed for easy client integration with clear workflow documentation.
- Lite package with only core reusable files and minimal dependencies.
Metadata
Frequently Asked Questions
What is 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 wh... It is an AI Agent Skill for Claude Code / OpenClaw, with 311 downloads so far.
How do I install mcdonalds-mcp-order-lite?
Run "/install mcdonalds-mcp-order-lite" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is mcdonalds-mcp-order-lite free?
Yes, mcdonalds-mcp-order-lite is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does mcdonalds-mcp-order-lite support?
mcdonalds-mcp-order-lite is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created mcdonalds-mcp-order-lite?
It is built and maintained by danielliao (@danielliao); the current version is v1.0.0.
More Skills