Lazy MCP — Development skill for Claude Code
CLI tool to manage Claude Code MCP servers and memory files.
How to install Lazy MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open machjesusmoto/lazy-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Lazy MCP does
CLI tool to manage Claude Code MCP servers and memory files.
Alternatives in Development
- MCP Builder — Guide for creating high-quality MCP servers to integrate external APIs and services 94.1k ★
- MCP Python SDK — Python SDK for building MCP servers 22.3k ★
- Claude Code Everything You Need To Know — Ultimate all-in-one guide to mastering Claude Code 1.3k ★
README
Lazy MCP
[](https://www.npmjs.com/package/lazy-mcp) [](https://github.com/machjesusmoto/lazy-mcp/actions/workflows/ci.yml) [](https://opensource.org/licenses/MIT)
Intelligent lazy-loading for Claude Code MCP tools. Let the agent decide what tools to load based on usage patterns and context needs.
Overview
Lazy MCP is a Claude Code plugin that enables **agent-driven tool loading** with intelligent context optimization. Instead of loading all available MCP servers upfront (consuming precious context window space), Lazy MCP uses a registry-based approach to inform Claude about available tools and loads them on-demand based on your actual needs.
**What It Does**:
- Agent-Driven Loading: Claude intelligently requests tools based on conversation analysis
- Registry-Informed: Maintains a registry of tool capabilities, keywords, and usage patterns
- Lazy Loading: Tools are loaded only when needed, then purged when usage ceases
- Context Optimization: Automatically manages context window to prevent limitations
- Profile Support: Save and switch between different tool configurations
The Problem
Traditional MCP integration loads all configured servers at session start, quickly consuming your context window with tools you may never use in a particular conversation. This leads to:
- Frequent context limit errors
- Wasted tokens on unused tool definitions
- Poor agent performance due to context clutter
The Solution
Lazy MCP uses a **registry + lazy loading** approach:
- Registry: Maintains metadata about all available tools (capabilities, keywords, usage patterns)
- Agent Analysis: Claude analyzes your request and identifies potentially useful tools
- On-Demand Loading: Only requested tools are loaded into context
- **I
Related Skills
Claude Code Gui
A comprehensive desktop GUI wrapper for Claude Code CLI — manage terminal sessions, CLAUDE.md, memory, MCP ser
MCP Gateway
Local MCP gateway that fans out to N downstream MCP servers, namespaces tools, and lazy-loads schemas — so you
Agent Backup
macOS app to back up coding-agent settings (MCP servers, sessions, memory, skills) to Google Drive with end-to
XCAgentHub
Manage the MCP servers and skills of the coding agents in Xcode
Tool Factory
A self-healing lifecycle system for Claude Code tools. Build, score, refurbish, and manage skills, agents, hoo
MCP Manager
Manage MCP servers across Claude Code, Cursor, Codex, and OpenCode
Related Agents
Configurator
Pitwall's built-in assistant for reconfiguring Claude Code (plugins, skills, MCP servers, hooks, memory files)
Raider Test Writer
Write Langertha::Raider tests with Test2::V0 — agent loop, MCP tool calling, CLI/Hall/ACP behavior. Tests neve
Android Performance Engineer
Use this agent to review native Android code for performance problems — Jetpack Compose recomposition and stab