mcp-integration

Integrate MCP servers into Claude Code plugins via stdio, SSE, HTTP, and WebSocket.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/NGTPTE/TuriX-MarketPlace --skill mcp-integration-ngtpte
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-integration
Source: https://github.com/NGTPTE/TuriX-MarketPlace/tree/main/plugins/plugin-dev/skills/mcp-integration
Command: npx skills add https://github.com/NGTPTE/TuriX-MarketPlace --skill mcp-integration-ngtpte

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you connect Claude Code plugins to external services and APIs through Model Context Protocol servers, so plugins can do more than local prompt logic alone.

Core Features & Use Cases

  • Server Integration: Configure local stdio servers, hosted SSE endpoints, HTTP APIs, or WebSocket connections for plugin tool access.
  • Authentication Guidance: Support OAuth, bearer tokens, custom headers, and environment-variable-based secrets with clear setup practices.
  • Workflow Enablement: Use MCP tools in commands and agents for database access, SaaS automation, multi-server orchestration, and external service workflows.

Quick Start

Ask the AI to add MCP integration to your plugin by choosing the right server type, wiring in the configuration, and documenting the required environment variables and tool usage.

Frequently Asked Questions about mcp-integration

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

FAQPage Schema
How do I connect Claude Code plugins to external MCP servers?

To connect Claude Code plugins to external MCP servers, you configure local stdio servers, hosted SSE endpoints, HTTP APIs, or WebSocket connections using portable ${CLAUDE_PLUGIN_ROOT} paths and environment-variable-based secrets for tool access.

What authentication methods can I use for MCP server integration?

MCP server integration supports OAuth, bearer tokens, custom headers, and environment-variable-based secrets, requiring clear setup practices and documented connection handling to securely manage external tool authentication.

How does Model Context Protocol work with Claude Code plugins?

Model Context Protocol works with Claude Code plugins by enabling them to access external services, databases, and SaaS automation through configured servers, expanding plugin capabilities beyond local prompt logic alone.

Can I configure multiple MCP servers in a single Claude Code plugin?

Yes, you can configure multiple MCP servers in a single Claude Code plugin to enable multi-server orchestration, allowing commands and agents to access databases, SaaS platforms, and external service workflows simultaneously.

What's the best way to manage secrets when integrating MCP tools?

The best way to manage secrets when integrating MCP tools is using environment-variable-based configurations, keeping sensitive data like bearer tokens and OAuth credentials out of the codebase while ensuring documented connection handling.

Why do I need portable paths for MCP server configuration in plugins?

You need portable ${CLAUDE_PLUGIN_ROOT} paths for MCP server configuration to ensure the plugin correctly locates local stdio servers and resources across different environments without breaking connection paths.