What is the Model Context Protocol (MCP)?

MCP is an open protocol that enables AI agents to connect to external tools and data sources, such as databases, local filesystems, or web APIs, in a standardized way.

Where are discovered tools stored for reference?

The skill persists the complete tool catalog to a local JSON file (assets/tools.json) for fast reference, intent analysis, and offline browsing.

Does this require the Gemini CLI to function?

While Gemini CLI is the recommended primary method for fast tool execution, the skill includes direct scripts and subagent-based delegation as effective fallbacks.

How does this skill help with context window management?

It uses progressive disclosure, loading only the necessary tool definitions and delegating execution to subagents or CLI tools to avoid cluttering the main conversation context.

Can I manage multiple MCP servers at once?

Yes, this skill supports multi-server orchestration, allowing you to aggregate and route commands to different configured servers from a central interface.

MCP Manager

Name: MCP Manager
Author: rafaelcalleja

byrafaelcalleja

•

Herramientas para Desarrolladores

Manages Model Context Protocol (MCP) servers to discover, analyze, and execute external tools and resources within AI agent workflows.

Acerca de

The MCP Management skill streamlines interaction with Model Context Protocol (MCP) servers, allowing Claude to connect seamlessly with external data sources and tools. It prevents context window bloat by utilizing progressive disclosure and subagent delegation to discover capabilities only when needed, maintaining a clean workspace while providing access to complex multi-server configurations. Whether listing available tools, analyzing JSON schemas for intent matching, or executing tasks via the Gemini CLI, this skill provides the essential infrastructure for building and managing robust AI agent integrations.

Características Principales

Multi-server management from a single configuration file
Progressive disclosure of capabilities to optimize context window usage
Seamless integration with Gemini CLI for high-speed tool execution
Automated tool discovery and persistence to structured JSON catalogs
Intelligent LLM-driven tool selection based on task intent and schema analysis
1 GitHub stars

Casos de Uso

Building and debugging MCP client implementations with persistent capability logging
Automating tool discovery across multiple MCP servers for complex developer workflows
Reducing context window pollution by delegating tool execution to specialized subagents

Acerca de

Características Principales

Multi-server management from a single configuration file
Progressive disclosure of capabilities to optimize context window usage
Seamless integration with Gemini CLI for high-speed tool execution
Automated tool discovery and persistence to structured JSON catalogs
Intelligent LLM-driven tool selection based on task intent and schema analysis
1 GitHub stars

Casos de Uso

Building and debugging MCP client implementations with persistent capability logging
Automating tool discovery across multiple MCP servers for complex developer workflows
Reducing context window pollution by delegating tool execution to specialized subagents