The Agent Skills Directory

[SAFE]: The skill communicates with mcp.mcd.cn, which is the official endpoint for the vendor's service as described in the documentation. No unauthorized external domains were detected.
[SAFE]: Authentication tokens are managed using a dedicated script (token-manager.py) that stores data in ~/.mcd-tokens.json. The script explicitly sets file permissions to 0o600 (read/write for the owner only) using os.chmod, which is a security best practice for local secret storage.
[SAFE]: The Python and Bash scripts use standard libraries and well-known tools (httpx, requests, curl, jq) to perform structured JSON-RPC calls. There is no evidence of obfuscation or dynamic code execution.
[COMMAND_EXECUTION]: The skill uses local Python and Bash scripts to perform its operations. This is the intended primary purpose of the skill to provide a command-line interface for the MCP service.

mcdonalds-coupons