The Agent Skills Directory

[SAFE]: The skill performs legitimate management of MCP configurations by interacting with local configuration files.
[COMMAND_EXECUTION]: The script scripts/health_check.py uses subprocess.run to verify the existence of configured MCP commands. It uses the which utility to check for binary availability (e.g., which npx), which is a standard and safe implementation for health monitoring.
[DATA_ACCESS]: The skill accesses ~/.claude.json to read and manage MCP server configurations. This access is necessary for the skill's primary purpose of managing MCP servers on the user's system, and no unauthorized data exposure or exfiltration was detected.

mcp-manager