mcp-management

Manage MCP servers and execute their tools from a configuration file.

1|1|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/Thanh-apero/apero-kit-cli --skill mcp-management-thanh-apero
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-management
Source: https://github.com/Thanh-apero/apero-kit-cli/tree/main/templates/skills/mcp-management
Command: npx skills add https://github.com/Thanh-apero/apero-kit-cli --skill mcp-management-thanh-apero

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @modelcontextprotocol/sdk, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This skill streamlines the management and execution of Model Context Protocol (MCP) servers, enabling efficient integration and utilization of external tools and data sources.

Core Features & Use Cases

  • Multi-Server Management: Connect and manage multiple MCP servers from a single configuration file.
  • Intelligent Tool Discovery: Automatically analyze and select relevant tools for specific tasks.
  • Progressive Disclosure: Load only necessary tool definitions to enhance context efficiency.
  • Execution Engine: Call MCP tools with proper parameter handling.
  • Context Efficiency: Delegate MCP operations to subagents to keep the main context clean.
  • Use Case: Imagine you need to search the web and save results. The skill would use the mcp-manager subagent to discover the brave-search tool, execute it, and save the results without cluttering the main context.

Quick Start

Use the mcp-management skill to list available tools by running the following command:

npx ts-node scripts/cli.ts list-tools

Frequently Asked Questions about mcp-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage multiple Model Context Protocol servers without polluting the main agent context?

Manage multiple MCP servers by using a centralized configuration file and delegating operations to subagents. This approach isolates tool execution, keeping your main AI agent context clean and efficient.

What is progressive disclosure for MCP tool discovery?

Progressive disclosure in MCP tool discovery means loading only the necessary tool definitions for a specific task. This mechanism prevents context pollution by analyzing and selecting relevant tools on demand.

How to execute MCP tools with proper parameter handling for AI agents?

Execute MCP tools by passing proper parameters through a dedicated execution engine. The system analyzes available capabilities and handles parameter mapping automatically to ensure correct tool invocation.

Does the Model Context Protocol SDK support multi-server management for subagents?

Yes, the Model Context Protocol SDK supports multi-server management. You can connect and interact with multiple configured MCP servers, delegating tool discovery and execution to subagents for context efficiency.

What's the best way to list available MCP tools from configured servers?

List available MCP tools by running a simple CLI command provided by the management scripts. This utility discovers and analyzes all capabilities from your configured servers without loading unnecessary definitions.