ck:mcp-management

Manage MCP servers to discover, analyze, and execute external tools via JSON-RPC.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/hidonguyen/trade-ops --skill ck-mcp-management-hidonguyen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:mcp-management
Source: https://github.com/hidonguyen/trade-ops/tree/main/.opencode/skills/mcp-management
Command: npx skills add https://github.com/hidonguyen/trade-ops --skill ck-mcp-management-hidonguyen

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 prevents main-agent context pollution by discovering, analyzing, and executing Model Context Protocol (MCP) tool, prompt, and resource capabilities in an isolated subagent environment so LLMs can orchestrate external tools reliably.

Core Features & Use Cases

  • Multi-server orchestration: Load and manage multiple MCP servers from a single configuration file to aggregate tool, prompt, and resource catalogs.
  • Intelligent tool discovery & selection: Persist discovered capabilities to assets/tools.json for LLM-driven analysis and context-efficient tool selection.
  • Execution engine & fallbacks: Run tools via Gemini CLI when available, fall back to direct Node scripts and the mcp-manager subagent; includes lifecycle management, timeouts, and graceful cleanup.
  • Use case: Automatically discover web-search, browser automation, and memory tools across servers, select the best tool for a research task, execute it, and save structured results.

Quick Start

Use the mcp-management skill to list all tools across configured MCP servers and save the catalog to assets/tools.json.

Frequently Asked Questions about ck:mcp-management

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

FAQPage Schema
How do I manage multiple MCP servers and list their tools without polluting the main agent context?

To orchestrate multiple MCP servers without context pollution, discover and execute tool, prompt, and resource capabilities in an isolated subagent environment. This skill loads multiple servers from a single configuration file to aggregate catalogs cleanly.

What is the best way to discover and select MCP tools for CLI and Gemini integration?

The best way to discover MCP tools for CLI and Gemini integration is to persist discovered capabilities to a JSON file for LLM-driven analysis. This enables context-efficient tool selection across web search, memory operations, and browser automation.

How do I execute JSON-RPC tool calls over stdio transport for external automation tasks?

Executing JSON-RPC tool calls over stdio transport requires subprocess management with lifecycle handling, timeouts, and graceful cleanup. This skill runs tools via Gemini CLI when available and falls back to direct Node scripts and an mcp-manager subagent.

Does this MCP management approach apply to orchestrating web search and browser automation tools together?

Yes, this MCP management approach applies to orchestrating web search, browser automation, and memory operations across servers. It automatically discovers these tools, selects the best one for a task, executes it, and saves structured JSON results.

Do I need the @modelcontextprotocol/sdk dependency to use this MCP server management skill?

Yes, the @modelcontextprotocol/sdk is a required dependency for this skill. It provides the foundational SDK needed to handle configuration loading, JSON-RPC tool listing and calling, and stdio transport subprocess management.

Why does my main agent context window overflow when loading too many MCP server capabilities?

Main agent context windows overflow when MCP server capabilities are loaded directly into the prompt. This skill prevents context pollution by using progressive disclosure of schemas and isolating tool discovery and execution within a subagent environment.