Mcporter Cli

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type gene...

This skill is an instruction wrapper for an external mcporter CLI. Before installing or using it: 1) Verify the npm package 'mcporter' and its publisher (check the package page, README, and source repository) and prefer installing from a trustworthy registry; 2) Be aware mcporter may perform network calls to servers you specify and will store auth tokens/config at ./config/mcporter.json by default — treat that file as sensitive; 3) Confirm the homepage/owner information (there is a mismatch between registry metadata and the included _meta.json ownerId) to ensure you're installing the intended project; 4) For initial use, run the CLI in a controlled environment (sandbox or VM) and inspect the config file created by mcporter to see what credentials are stored.

Type: OpenClaw Skill Name: mcporter-cli Version: 1.0.1 The mcporter-cli skill provides a wrapper for the mcporter tool, which includes high-risk capabilities such as executing arbitrary commands via stdio (e.g., `mcporter call --stdio "bun run ./server.ts"`) and managing sensitive authentication credentials (`mcporter auth` and `mcporter config`). While these functions are consistent with the stated purpose of interacting with Model Context Protocol (MCP) servers, they grant the AI agent broad execution and configuration permissions that could be leveraged for unauthorized actions if the agent is misdirected. The skill is classified as suspicious due to these inherent high-risk capabilities (SKILL.md).