mcp

Create and manage MCP servers and tools for LLM integration.

Updated Nov 20, 2025
One-click install
npx skills add https://github.com/wollfoo/codex-cli --skill mcp-wollfoo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp
Source: https://github.com/wollfoo/codex-cli/tree/main/skills/mcp
Command: npx skills add https://github.com/wollfoo/codex-cli --skill mcp-wollfoo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the development and management of MCP (Model Context Protocol) servers and tools, enabling seamless integration between LLMs and external services.

Core Features & Use Cases

  • Build MCP Servers: Create Python (FastMCP) or TypeScript (MCP SDK) servers, design tool schemas, and write evaluations.
  • Manage/Use MCP Tools: Discover, execute, and configure MCP tools across multiple servers, integrating with tools like Gemini CLI.
  • Use Case: A developer needs to build a new MCP server to expose a company's internal API to an LLM. They use the BUILD mode to define the tools and schemas. Later, a product manager uses the MANAGE mode to discover and test these newly created tools.

Quick Start

Use the mcp skill to create a new MCP server for managing user profiles.

Frequently Asked Questions about mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an MCP server for LLM integration?

Yes, you can build MCP servers using TypeScript via the MCP SDK. This allows you to design tool schemas, write evaluations, and expose external service APIs to LLMs using a structured communication protocol.

What is the best way to manage and execute MCP tools across multiple servers?

The best way to manage MCP tools across multiple servers is using the MANAGE mode to discover, execute, and configure them via CLI or subagents. This handles structured tool execution and integration with environments like Gemini CLI.

Does MCP protocol support Python for server development?

Yes, MCP protocol supports Python server development through FastMCP. You can use it to create servers, design tool schemas, and expose internal APIs to LLMs for structured communication.

Can I use MCP tools with Gemini CLI for external API integration?

Yes, you can configure and execute MCP tools with Gemini CLI. The MANAGE mode discovers and integrates these tools across multiple servers, enabling structured communication between LLMs and external services.

When do I need to design tool schemas for MCP servers?

You need to design tool schemas for MCP servers when exposing internal APIs or external services to LLMs. This structured approach defines how models interact with specific tools during server development.