mcporter

Manage MCP servers and tools from the command line via CLI.

2|Updated Jun 8, 2026
One-click install
npx skills add https://github.com/vikrant-project/devil-agent-ai-platform --skill mcporter-vikrant-project
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcporter
Source: https://github.com/vikrant-project/devil-agent-ai-platform/tree/main/agent_core/optional-skills/mcp/mcporter
Command: npx skills add https://github.com/vikrant-project/devil-agent-ai-platform --skill mcporter-vikrant-project

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a straightforward and efficient way to interact with Model Context Protocol (MCP) servers and tools directly from the command line, enabling users to list, configure, authenticate, and invoke tools on demand.

Core Features & Use Cases

  • Direct MCP Server Management: Execute commands to list, configure, and call MCP servers.
  • Ad-Hoc Server Connection: Establish connections to ad-hoc servers via HTTP URLs or stdio commands.
  • Tool Invocation: Run specific tools from a server, using key=value syntax, function syntax, or JSON payloads.
  • Authentication and Configuration: Manage OAuth logins and server configurations.
  • Daemon Mode: Maintain persistent connections to servers for ongoing operations.
  • Code Generation: Generate CLI wrappers and TypeScript clients for MCP servers.
  • Use Case: Quickly access and manipulate MCP services for data processing, model management, or API interactions in your workflow.

Quick Start

List all configured MCP servers using mcporter list.

Frequently Asked Questions about mcporter

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

FAQPage Schema
How do I manage Model Context Protocol servers from the command line?

You can manage Model Context Protocol servers from the command line by using a dedicated CLI to list, configure, and invoke tools on demand. This enables direct server discovery and interaction for automation workflows.

Can I connect to an ad-hoc MCP server via HTTP or stdio?

Yes, you can establish ad-hoc connections to MCP servers via HTTP URLs or stdio commands. This enables flexible, on-the-fly tool invocation without requiring permanent configuration changes.

Do I need Node.js to configure and call MCP tools?

Yes, Node.js is required as a dependency to run the CLI and interact with MCP servers. You also need specific MCP client configurations to properly authenticate and execute tool invocations.

How do I invoke specific tools on an MCP server using key=value syntax?

You can invoke specific tools on an MCP server using key=value syntax, function syntax, or JSON payloads. The CLI handles request execution and returns the tool output directly to your terminal.

What is the best way to maintain persistent connections to MCP servers?

The best way to maintain persistent connections to MCP servers is by using daemon mode. This keeps connections alive for ongoing operations, preventing the need to re-authenticate for repeated tool invocations.

Can I generate TypeScript clients for Model Context Protocol servers?

Yes, you can generate CLI wrappers and TypeScript clients for MCP servers. This allows you to integrate server interactions directly into your codebase for automated data processing and API workflows.