mcp-management

Coordinate multiple MCP servers for tool discovery and execution.

Updated Jun 16, 2025
One-click install
npx skills add https://github.com/Stonelukas/Mouse-on-Numpad --skill mcp-management-stonelukas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-management
Source: https://github.com/Stonelukas/Mouse-on-Numpad/tree/main/.opencode/skill/mcp-management
Command: npx skills add https://github.com/Stonelukas/Mouse-on-Numpad --skill mcp-management-stonelukas

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Coordinating and orchestrating multiple MCP servers for discovery, analysis, and execution of capabilities without polluting the main context.

Core Features & Use Cases

  • Multi-server MCP management: Connect to and coordinate multiple MCP servers from a single config.
  • Progressive capability discovery: List tools, prompts, and resources and load only what’s needed for a task.
  • Intelligent analysis and execution: Choose relevant tools via LLM guidance and execute with proper parameter handling.
  • Context-efficient integration: Delegate MCP operations to subagents to keep the main agent context clean.
  • Persistent catalog: Save discovered tools to assets/tools.json for fast offline reference.
  • Gemini CLI integration: Primary interface via Gemini CLI for structured, prompt-driven workflows; fallback to direct scripts if Gemini is unavailable.

Quick Start

Install dependencies and run the MCP management CLI to list tools across 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 polluting the main LLM context?

You can manage multiple MCP servers without polluting context by delegating discovery and execution operations to subagents. This approach keeps the main agent context clean while coordinating tools, prompts, and resources across servers.

How do I list available tools and prompts across configured MCP servers?

You can list available tools and prompts across configured MCP servers by running CLI commands like list-tools, list-prompts, and list-resources. The system loads configurations from .opencode/.mcp.json to connect and discover capabilities.

What is the best way to coordinate tool discovery and execution for AI workflows?

The best way to coordinate tool discovery and execution for AI workflows is using a multi-server MCP management system. It uses LLM guidance to analyze relevance and handles parameter execution efficiently.

Can I save discovered MCP tools for offline reference?

Yes, you can save discovered MCP tools for offline reference. The system creates a persistent catalog by saving discovered capabilities to assets/tools.json, enabling fast offline lookups.

Does MCP management work with Gemini CLI for prompt-driven workflows?

Yes, MCP management works with Gemini CLI for prompt-driven workflows. Gemini CLI serves as the primary interface for structured interactions, with fallback to direct scripts if unavailable.