The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and SDK information from the official Model Context Protocol website (modelcontextprotocol.io) and its associated GitHub repositories. These are well-known and trusted sources for the protocol being implemented.
[COMMAND_EXECUTION]: The scripts/connections.py and scripts/evaluation.py files include logic to execute local MCP servers via the stdio transport. This is a core feature of the Model Context Protocol, allowing an LLM to interact with local services as subprocesses. The implementation uses the official mcp Python library for this purpose.
[SAFE]: The skill follows security best practices by recommending environment variables for API keys and specifying that standard input/output (stdio) servers should not log to stdout to prevent protocol interference. No signs of obfuscation, data exfiltration, or malicious prompt injection were detected.

mcp-builder