mcporter

Manage MCP servers and tools through the mcporter CLI with HTTP or stdio connections.

641|104|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/loongclaw-ai/loongclaw --skill mcporter-loongclaw-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcporter
Source: https://github.com/loongclaw-ai/loongclaw/tree/main/skills/mcporter
Command: npx skills add https://github.com/loongclaw-ai/loongclaw --skill mcporter-loongclaw-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Managing MCP servers and their exposed tools usually means juggling discovery registries, config files, and interactive auth flows, so mcporter centralizes discovery, configuration, authentication, and invocation into a single command-line workflow.

Core Features & Use Cases

  • Unified discovery and listing of MCP servers across installed clients plus ad-hoc HTTP or stdio endpoints so you immediately see all reachable tools without manual config edits.
  • Credential and config management that lets you run oauth flows, inspect and edit stored values, import settings, and manage a daemon for persistent connections while still using the same CLI.
  • Use case: while building a vertical agent you can call a tool such as linear.list_issues with filters, then emit a CLI wrapper or generate TypeScript types for automation pipelines.

Quick Start

Manage your MCP workflow by using mcporter to list configured servers and then invoking linear.list_issues with team=ENG and limit=5 filters to exercise a tool.

Frequently Asked Questions about mcporter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage MCP servers from the command line?

You can manage MCP servers from the command line by using a CLI tool to list configured servers, edit configurations, run authentication flows, and invoke exposed tools directly. It consolidates discovery and invocation into a single workflow.

Can I generate TypeScript types from MCP server tools?

Yes, you can generate TypeScript types and CLI wrappers from MCP server tools. This allows you to build automation pipelines by creating typed clients for endpoints you discover and authenticate with via the CLI.

How do I invoke an MCP tool with specific arguments from a terminal?

You invoke an MCP tool from a terminal by passing the tool name along with key=value or JSON formatted arguments. The CLI processes these arguments and can emit machine-readable JSON output for the response.

Do I need Node.js to configure and run MCP endpoints?

Yes, you need Node.js installed with npx or npm to configure and run MCP endpoints. The CLI relies on the Node.js environment to manage server connections, handle authentication, and execute tool invocations.

What is the best way to connect to ad-hoc MCP servers?

The best way to connect to ad-hoc MCP servers is using a unified CLI that supports direct HTTP or stdio connections. This allows immediate tool discovery and invocation without requiring manual config file edits beforehand.

Why does managing MCP servers require a daemon process?

Managing MCP servers may require a daemon process to maintain persistent connections to endpoints. The CLI can manage this daemon alongside stored credentials and configurations, ensuring continuous access to tools across terminal sessions.