This skill should be used when the user asks to "add MCP server", "configure .mcp.json", "integrate external API", or mentions Model Context Protocol, stdio server, SSE server, or MCP tools.
Configures Model Context Protocol servers to integrate external APIs and services with Claude Code.
/plugin marketplace add GGPrompts/my-plugins/plugin install plugin-dev@my-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Model Context Protocol (MCP) enables Claude Code plugins to connect with external services and APIs through structured tool access.
Method 1: Dedicated .mcp.json (Recommended)
{
"mcpServers": {
"server-name": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/servers/server.js"],
"env": {
"API_KEY": "${API_KEY}"
}
}
}
}
Method 2: Inline in plugin.json
{
"name": "my-plugin",
"mcpServers": {
"server-name": { ... }
}
}
| Type | Use Case | Example |
|---|---|---|
| stdio | Local process | Custom tools, local APIs |
| SSE | Hosted servers with OAuth | Asana, GitHub, etc. |
| HTTP | REST API with tokens | Custom backends |
| WebSocket | Real-time bidirectional | Streaming data |
{
"mcpServers": {
"my-tools": {
"command": "python",
"args": ["${CLAUDE_PLUGIN_ROOT}/server.py"],
"env": { "DEBUG": "true" }
}
}
}
{
"mcpServers": {
"github": {
"type": "sse",
"url": "https://mcp.github.com/sse"
}
}
}
{
"mcpServers": {
"api": {
"type": "http",
"url": "https://api.example.com/mcp",
"headers": {
"Authorization": "Bearer ${API_TOKEN}"
}
}
}
}
MCP tools follow this pattern:
mcp__plugin_<plugin-name>_<server-name>__<tool-name>
Pre-allow specific tools in command frontmatter:
allowed-tools: mcp__plugin_my-plugin_server__specific-tool
mcp__plugin_ prefix# Verify server appears
/mcp
# Debug logs
claude --debug
# Test tool calls
# Use specific tool in conversation
Always use for portability:
${CLAUDE_PLUGIN_ROOT} - Plugin directory${API_KEY}, ${TOKEN} - Secrets from user environmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.