Mcp Management

This handles MCP server management without cluttering your main context window. It discovers tools, prompts, and resources from configured servers, then lets you filter and execute them either through Gemini CLI (fastest), direct TypeScript scripts, or a fallback subagent. The smart move here is how it saves discovered tools to JSON so an LLM can analyze them directly instead of loading everything upfront. You configure servers once in `.claude/.mcp.json`, and it coordinates across multiple servers while keeping track of which tool belongs where. Honestly most useful when you're dealing with context bloat from too many MCP capabilities or need programmatic control over tool execution.

skills.sh installs: 393
GitHub stars: 248
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add secondsky/claude-skills --skill mcp-management --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Management

Skill for managing and interacting with Model Context Protocol (MCP) servers.

Overview

MCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.

Key Benefits:

Progressive disclosure of MCP capabilities (load only what's needed)
Intelligent tool/prompt/resource selection based on task requirements
Multi-server management from single config file
Context-efficient: subagents handle MCP discovery and execution
Persistent tool catalog: automatically saves discovered tools to JSON for fast reference