ck:mcp-management

Discover, analyze, and execute MCP tools across multiple servers via CLI.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/hotriluan/alkana_web --skill ck-mcp-management-hotriluan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:mcp-management
Source: https://github.com/hotriluan/alkana_web/tree/main/.opencode/skills/mcp-management
Command: npx skills add https://github.com/hotriluan/alkana_web --skill ck-mcp-management-hotriluan

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 and cross-server tool execution without polluting the main context window, enabling efficient integration of external tools and services.

Core Features & Use Cases

  • Multi-server management: connect to and coordinate capabilities from several MCP servers from a single config.
  • Intelligent tool discovery and selection: analyze available tools, prompts, and resources to match task requirements.
  • Progressive disclosure: load only the necessary tool definitions when required, reducing context size.
  • Context-efficient execution: delegate MCP interactions to subagents to keep the main assistant context lean.
  • Persistent catalog: automatically save discovered tools to JSON for fast reference and offline exploration.

Quick Start

Configure your MCP servers in .opencode/.mcp.json, install dependencies, and run the CLI to discover tools and execute tasks.

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 without polluting the main LLM context window?

You can manage multiple MCP servers without polluting the main LLM context window by delegating MCP interactions to subagents. This approach enables context-efficient execution by loading only necessary tool definitions when required.

How do I discover and execute tools across multiple MCP servers using a unified CLI?

You can discover and execute tools across multiple MCP servers by configuring connections via a .opencode/.mcp.json file and running a unified CLI. This process supports listing tools, prompts, and resources, and executes tasks within task-based workflows.

Can I use @modelcontextprotocol/sdk to connect and coordinate capabilities from several MCP servers?

Yes, you can use @modelcontextprotocol/sdk to connect and coordinate capabilities from several MCP servers. Multi-server management is achieved through configuration-driven connections, allowing you to coordinate capabilities from a single config.

What is progressive disclosure in MCP tool discovery and how does it reduce context size?

Progressive disclosure in MCP tool discovery is the practice of loading only the necessary tool definitions when required. This technique directly reduces context size by preventing the loading of unused tool schemas into the main assistant context.

Does MCP management support saving discovered tools for offline exploration?

Yes, MCP management supports saving discovered tools for offline exploration. It automatically saves discovered tools to a persistent JSON catalog, which serves as a fast reference for offline exploration and subsequent task execution.