The Agent Skills Directory

[SAFE]: The skill provides legitimate guidance, documentation, and code templates for building applications with the Model Context Protocol (MCP).
[COMMAND_EXECUTION]: Instructs the use of standard package managers like npx and pip to install official development tools such as @modelcontextprotocol/create-server and @modelcontextprotocol/inspector.
[EXTERNAL_DOWNLOADS]: References official and well-known packages from the @modelcontextprotocol namespace on NPM and the mcp package on PyPI.
[DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were detected. The skill specifically includes constraints against exposing sensitive data and hardcoding credentials.
[PROMPT_INJECTION]: No evidence of prompt injection, role-play overrides, or instructions to bypass safety filters was found.

mcp-developer