ck:mcp-management

Centralize discovery and orchestration of MCP servers via CLI.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/quanganh208/cookmate --skill ck-mcp-management-quanganh208
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:mcp-management
Source: https://github.com/quanganh208/cookmate/tree/main/.opencode/skills/mcp-management
Command: npx skills add https://github.com/quanganh208/cookmate --skill ck-mcp-management-quanganh208

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Centralizes the discovery, analysis, and execution of MCP (Model Context Protocol) capabilities across multiple servers, enabling context-efficient integration without cluttering the main AI context.

Core Features & Use Cases

  • Multi-Server Management: Connect to and orchestrate MCP servers from a single configuration.
  • Intelligent Tool Discovery: Analyze which tools/prompts/resources are relevant for a given task.
  • Progressive Disclosure: Load only the necessary tool definitions to minimize context load.
  • Execution Engine: Execute MCP tools with proper parameter handling via a CLI or subagent workflow.
  • Context Efficiency: Keep the main agent context clean by delegating MCP operations to dedicated subagents.

Quick Start

Configure MCP servers in .opencode/.mcp.json, install dependencies, and use the MCP CLI to list tools or call a tool to begin 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 cluttering the main agent context?

Manage multiple MCP servers using centralized discovery and orchestration with progressive disclosure. This approach loads only necessary tool definitions via dedicated subagents, keeping the main AI context clean and minimizing load.

How do I discover and call tools across different MCP servers?

Discover and call tools across MCP servers using a CLI-driven interface. You can list-tools, list-prompts, list-resources, and execute call-tool operations with proper parameter handling and error support across configured servers.

What is the best way to orchestrate Model Context Protocol servers for context-efficient tool access?

The best way to orchestrate Model Context Protocol servers is through centralized config-based management. This enables intelligent tool discovery and progressive disclosure, loading only relevant capabilities to ensure safe, context-efficient tool access.

Can I use a single configuration file to connect and run tools across multi-server MCP integrations?

Yes, you can connect and run tools across multi-server MCP integrations from a single configuration. Define your servers in the configuration file, then use the CLI to validate configurations and execute tools or prompts.

Does this MCP orchestration approach support environment variables and error handling for tool execution?

Yes, MCP orchestration supports environment variables and error handling for tool execution. The execution engine manages parameters safely and handles errors during call-tool operations across the connected servers.