Which MCP transport types are supported?

This skill covers four primary transport methods: local process (stdio), Server-Sent Events (SSE), RESTful APIs (HTTP), and WebSockets (WS).

What is the Model Context Protocol (MCP)?

MCP is an open standard that enables AI models like Claude to securely access data and tools from external services through a unified interface.

Can I use multiple MCP servers in a single plugin?

Yes, you can define multiple servers within a .mcp.json file or the mcpServers field in plugin.json to create complex, multi-service workflows.

How do I debug my MCP connection?

You can use the /mcp command within Claude Code to view active servers and run 'claude --debug' to inspect connection logs and tool discovery errors.

How do I secure API keys in my MCP plugin?

Use environment variable expansion (e.g., ${API_KEY}) in your configuration files to avoid hardcoding sensitive credentials in your codebase.

MCP Integration for Claude Code

Name: MCP Integration for Claude Code
Author: nsalvacao

bynsalvacao

0•

API 开发

Integrates external tools and services into Claude Code using the Model Context Protocol (MCP) for expanded AI capabilities.

This skill provides a comprehensive framework for connecting Claude Code plugins to external data sources, APIs, and local processes through the Model Context Protocol. It streamlines the implementation of various transport layers—including stdio, SSE, HTTP, and WebSockets—while ensuring secure environment variable management and standardized tool naming conventions. By following these established patterns, developers can build robust, production-grade plugins that allow Claude to interact autonomously with third-party ecosystems like GitHub, Asana, or custom databases.

主要功能

01Standardized .mcp.json and plugin.json configuration patterns

020 GitHub stars

03Automatic environment variable expansion and secure credential handling

04Multi-transport support for stdio, SSE, HTTP, and WebSocket connections

05Structured MCP tool naming and permission scoping for enhanced security

06Comprehensive lifecycle management and debug logging guidance

使用场景

01Connecting Claude Code to cloud-based project management tools via SSE and OAuth

02Building a database explorer plugin that uses stdio to query local SQL instances

03Creating custom real-time monitoring tools using WebSocket-based MCP servers

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nsalvacao/nsalvacao-claude-code-plugins mcp-integration

For use in Claude.ai and ChatGPT

主要功能

01Standardized .mcp.json and plugin.json configuration patterns

020 GitHub stars

03Automatic environment variable expansion and secure credential handling

04Multi-transport support for stdio, SSE, HTTP, and WebSocket connections

05Structured MCP tool naming and permission scoping for enhanced security

06Comprehensive lifecycle management and debug logging guidance

使用场景

01Connecting Claude Code to cloud-based project management tools via SSE and OAuth

02Building a database explorer plugin that uses stdio to query local SQL instances

03Creating custom real-time monitoring tools using WebSocket-based MCP servers

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nsalvacao/nsalvacao-claude-code-plugins mcp-integration

For use in Claude.ai and ChatGPT