mcp-cli

Discover, inspect, and execute MCP server tools from the command line.

Updated May 6, 2026
One-click install
npx skills add https://github.com/Takfes/indie-scaffolder --skill mcp-cli-takfes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-cli
Source: https://github.com/Takfes/indie-scaffolder/tree/main/components/agent-skills-commands/.agents/skills/mcp-cli
Command: npx skills add https://github.com/Takfes/indie-scaffolder --skill mcp-cli-takfes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork from interacting with MCP servers by helping you discover available tools, inspect their input schemas, and execute calls from the command line.

Core Features & Use Cases

  • Server discovery: List configured MCP servers and see what tools each one exposes.
  • Schema inspection: Check a tool’s exact JSON input shape before sending a request.
  • One-off tool execution: Call tools on servers like context7, zotero, playwright, tavily-remote-mcp, sequentialthinking, vibe_kanban, and notebooklm-mcp without adding them to permanent agent config.
  • Troubleshooting and prototyping: Debug server behavior, verify parameter types, and test integrations safely before committing to a fuller setup.

Quick Start

Use the mcp-cli skill to discover the target MCP server, inspect the tool schema, and run the tool with correctly formatted JSON arguments.

Frequently Asked Questions about mcp-cli

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

FAQPage Schema
How do I discover and call MCP server tools from the shell?

To discover and call MCP server tools from the shell, you use a dedicated CLI to list configured servers, inspect their tool input schemas, and execute one-off calls with exact JSON argument matching.

What is the best way to inspect an MCP tool's JSON input schema before executing a call?

Inspecting an MCP tool's JSON input schema is done by requesting schema review through the CLI, which reveals the exact parameter types and shapes required to execute a valid tool call.

Can I run one-off tool calls on servers like context7 or playwright without adding them to a permanent agent config?

Yes, you can run one-off tool calls on servers like context7 or playwright without permanent agent configuration by using the CLI for direct server discovery, schema inspection, and targeted execution.

How do I debug MCP server behavior and verify parameter types safely?

Debugging MCP server behavior and verifying parameter types safely involves using the CLI for troubleshooting and prototyping, allowing you to test integrations and validate exact JSON arguments before a fuller setup.

Why does my MCP tool execution fail when I pass arguments from the command line?

MCP tool execution from the command line typically fails when arguments do not match the tool's exact JSON input shape, requiring explicit configuration resolution and strict schema inspection prior to execution.