mcp-management

Discover, analyze, and execute MCP server capabilities without polluting the context window.

Updated Feb 3, 2026
One-click install
npx skills add https://github.com/lv7dev/shop_v2 --skill mcp-management-lv7dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-management
Source: https://github.com/lv7dev/shop_v2/tree/main/.claude/skills/mcp-management
Command: npx skills add https://github.com/lv7dev/shop_v2 --skill mcp-management-lv7dev

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 enables Claude to discover, analyze, and execute MCP (Model Context Protocol) server capabilities without polluting the main context window. It coordinates multiple MCP servers from a single config, supporting safe delegation to subagents and persistent catalogs for fast reference.

Core Features & Use Cases

  • Centralized MCP orchestration: connect to multiple MCP servers, list available tools, prompts, and resources.
  • Intelligent tool analysis: let the LLM select relevant tools for a given task, reducing unnecessary data in context.
  • Context-efficient execution: delegate discovery and execution to subagents (e.g., mcp-manager) to keep the main agent lean.
  • Use case: integrate with memory and filesystem MCP servers to perform cross-server data extraction, transformation, and action execution with a single task prompt.

Quick Start

  • Install dependencies: cd .claude/skills/mcp-management/scripts npm install
  • Ensure MCP config exists at .claude/.mcp.json describing your MCP servers.
  • List available tools/prompts/resources: npx tsx scripts/cli.ts list-tools npx tsx scripts/cli.ts list-prompts npx tsx scripts/cli.ts list-resources

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 context window?

Multi-server MCP orchestration keeps the main context window clean by delegating tool discovery and execution to a subagent. It loads tools, prompts, and resources on demand across configured servers.

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

You can list available tools, prompts, and resources by running the CLI script commands. This discovers capabilities across all configured MCP servers and persists a catalog for fast offline reference.

What is intelligent tool selection in the Model Context Protocol?

Intelligent tool selection analyzes available MCP server capabilities and selects only the relevant tools for a given task. This reduces unnecessary data in context and optimizes execution pathways.

Do I need a configuration file to connect to MCP servers?

Yes, MCP-management enforces configuration-driven connections and requires an MCP config file. This config describes your MCP servers and enables centralized orchestration for the execution pathways.

Can I use mcp-management with Gemini CLI for server execution?

Yes, MCP-management supports multiple execution pathways including Gemini CLI, direct scripts, or a dedicated mcp-manager subagent. This allows flexible cross-server data extraction and action execution.

What is the best way to execute cross-server data extraction with MCP?

The best way to execute cross-server data extraction is through centralized MCP orchestration. It connects to multiple servers like memory and filesystem MCP, allowing single-prompt transformation and action execution.