The Agent Skills Directory

[SAFE]: The skill serves as a development and testing guide for the Model Context Protocol (MCP). It includes legitimate Python scripts for establishing MCP connections and running evaluations using the Anthropic API.
[SAFE]: External references are limited to official Model Context Protocol documentation and SDK repositories on GitHub, which are trusted sources for this technology.
[SAFE]: The evaluation harness (evaluation.py) uses the mcp library to communicate with servers via standard input/output, which is the intended and standard operation for MCP tools.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or malicious persistence mechanisms was found within the instructions or supporting scripts.

mcp-builder