mcp-integration
Guidance for integrating MCP servers (SSE, stdio, HTTP, WebSocket) into Claude Code plugins via .mcp.json.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for mcp-integration, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Part of the plugin-dev plugin, this skill guides wiring Model Context Protocol servers into Claude Code plugins: using .mcp.json, the ${CLAUDE_PLUGIN_ROOT} variable, and different server types (SSE, stdio, HTTP, WebSocket) to connect external services. It bundles example server configs (stdio-server.json, sse-server.json, http-server.json) and reference docs on authentication and tool usage.
Key features and capabilities
- Server-type configs: stdio, SSE, HTTP
- ${CLAUDE_PLUGIN_ROOT} wiring
- Authentication and tool-usage references
Use cases
- Add an MCP server to a Claude Code plugin
- Configure a stdio or SSE MCP connection