The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the mcporter package from the official Node.js package registry (npm) during the setup process.
[COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands using the --stdio flag, which is designed to launch and communicate with local MCP servers (e.g., bun run ./server.ts).
[CREDENTIALS_UNSAFE]: The skill provides an interface for managing authentication and configuration via mcporter auth and mcporter config commands, which handle server access tokens and credentials.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes tool outputs and schemas from external MCP servers.
Ingestion points: Data enters the context through mcporter call responses from remote or local servers.
Boundary markers: No specific delimiters or safety instructions are applied to tool outputs in the provided documentation.
Capability inventory: Includes command execution, network requests, and code generation (generate-cli).
Sanitization: No explicit sanitization of tool output is documented.

mcporter