
from agentic-mcp-skill34
Interactive MCP server management using a three-layer progressive disclosure API and socket daemon for efficient tool execution.
This skill implements a high-efficiency interface for interacting with Model Context Protocol (MCP) servers. It utilizes a socket daemon to provide 'progressive disclosure'—fetching metadata first, then tool lists, then specific tool schemas only when needed—to minimize token usage and overhead.
Use this skill when you need to discover and execute tools from an MCP server without loading the entire server configuration into context. It is ideal for dynamic environment management where a variety of MCP servers are available.
start, stop, health), server discovery (metadata, list, schema), and tool execution (call).mcp-servers.json setup.Designed for advanced agents supporting Bash execution and JSON-based tool parameters, such as OpenClaw, Claude Code, and other ACP-compatible harnesses.
This skill has not been reviewed by our automated audit pipeline yet.