mcp-management

Orchestrate MCP servers to discover and execute tools, prompts, and resources.

Updated Jan 24, 2026

Search Tags:#cli #mcp #orchestration #subagent #multi-server #context-management #tool-discovery

Ready to run

npx skills add https://github.com/Khoatran1999/aquarium-commerce --skill mcp-management-khoatran1999

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mcp-management
Source: https://github.com/Khoatran1999/aquarium-commerce/tree/main/.claude/skills/mcp-management
Command: npx skills add https://github.com/Khoatran1999/aquarium-commerce --skill mcp-management-khoatran1999

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MCP-management solves the challenge of orchestrating multiple MCP servers and securely executing tools, prompts, and resources without cluttering the main AI context.

Core Features & Use Cases

Multi-server capability discovery and aggregation across MCP servers
Intelligent tool/prompt/resource analysis and selective loading
Context-efficient delegation via subagents for safe execution
Seamless tool invocation and results consolidation for downstream tasks
Supports centralized configuration and transition between servers for scalable MCP integrations

Quick Start

Run the MCP management CLI to list tools across all configured MCP servers.

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 MCP servers without cluttering the main AI context?▼

You can manage multiple MCP servers by using subagent-based execution to orchestrate and discover tools, prompts, and resources. This delegates execution safely, keeping your main context clean by selectively loading only necessary capabilities.

What is MCP multi-server discovery and how does it work?▼

MCP multi-server discovery is the process of aggregating and analyzing capabilities across configured MCP servers. It works by reading a JSON config file to list available tools, prompts, and resources, enabling intelligent tool selection for your workflow.

How do I list and execute tools across different MCP servers?▼

To list and execute tools across MCP servers, run the MCP CLI scripts provided. These scripts read your centralized configuration and use subagent-based execution to invoke tools and consolidate results for downstream tasks.

Do I need a specific configuration file to orchestrate MCP servers?▼

Yes, you need a JSON MCP config file located at .claude/.mcp.json. This centralized configuration file is required to enable multi-server discovery, intelligent tool selection, and seamless transitions between servers.

What is the best way to keep AI context clean when using MCP tools?▼

The best way to keep context clean is using subagent-based execution for MCP tool orchestration. This approach performs intelligent tool analysis and selective loading, preventing capability clutter from overwhelming the main context window.

Can I use @modelcontextprotocol/sdk to aggregate tools from multiple servers?▼

Yes, this Skill relies on @modelcontextprotocol/sdk to support multi-server capability discovery and aggregation. It enables seamless tool invocation and centralized configuration to scale your MCP integrations efficiently.