The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches protocol specifications and SDK documentation from official sources, specifically modelcontextprotocol.io and the modelcontextprotocol GitHub organization. These are the authoritative repositories for the technology described and are considered safe.
[COMMAND_EXECUTION]: The provided Python script scripts/evaluation.py acts as a test harness that executes local MCP servers via the stdio transport. It spawns subprocesses using commands and arguments provided by the user via command-line arguments (e.g., -c python -a my_server.py) to facilitate local testing and debugging.
[SAFE]: A thorough review of the skill's instructions, documentation, and scripts reveals no malicious patterns, obfuscation, data exfiltration, or persistence mechanisms. The capabilities provided are standard for developer-centric tools designed to build and verify AI-integrated services.

mcp-builder