mcp-management

Coordinates MCP discovery, analysis and execution across servers via mcp-manager subagent and CLI-driven workflows.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/lukebaze/forex-rebate-bot --skill mcp-management-lukebaze
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-management
Source: https://github.com/lukebaze/forex-rebate-bot/tree/main/.opencode/skill/mcp-management
Command: npx skills add https://github.com/lukebaze/forex-rebate-bot --skill mcp-management-lukebaze

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 servers are scattered across environments, making discovery and coordinated execution tedious. This skill centralizes discovery, analysis, and execution of MCP capabilities from configured servers without polluting the main context window.

Core Features & Use Cases

  • Multi-server MCP discovery from a single config
  • Intelligent tool analysis and on-demand loading to optimize context
  • Safe, delegated execution via a subagent architecture
  • Persisted tool catalog for fast reference across sessions

Quick Start

Configure your MCP servers in .opencode/.mcp.json and run the MCP CLI to list tools, prompts, and 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?

You can manage multiple MCP servers without polluting the main context window by using a subagent architecture to delegate discovery, intelligent tool analysis, and execution, ensuring only necessary results are loaded on demand.

How do I discover and list tools across different MCP server configurations?

To discover and list MCP tools, prompts, and resources, load your server configurations from the .opencode/.mcp.json file and run the CLI to automatically parse and centralize available server capabilities.

Does MCP management work with the @modelcontextprotocol/sdk for tool execution?

Yes, MCP management works with the @modelcontextprotocol/sdk to execute tools with structured inputs, coordinating safe execution via an mcp-manager subagent and supporting Gemini CLI-driven workflows.

What is the best way to orchestrate multi-server MCP tool discovery?

The best way to orchestrate multi-server MCP tool discovery is to centralize configuration management, persist a tool catalog for fast cross-session reference, and load tool details on demand to optimize context usage.

Why does my MCP server context window overflow when executing multiple tools?

Your context window overflows during tool execution when all tool data is loaded simultaneously; delegating execution via an mcp-manager subagent and persisting a tool catalog prevents this by loading details on demand.

Can I use MCP management to execute tools with structured inputs across different servers?

Yes, you can use MCP management to safely execute tools with structured inputs across different servers by delegating the execution tasks to the mcp-manager subagent, which isolates the processing logic.