ck:use-mcp

Automates MCP operations via Gemini CLI and mcp-manager subagent.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/EdgeHunt/EdgeHunt --skill ck-use-mcp-edgehunt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:use-mcp
Source: https://github.com/EdgeHunt/EdgeHunt/tree/main/.claude/skills/use-mcp
Command: npx skills add https://github.com/EdgeHunt/EdgeHunt --skill ck-use-mcp-edgehunt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates intelligent MCP orchestration, enabling seamless discovery and execution of MCP operations within Gemini and the mcp-manager subagent, preserving context and reducing manual steps.

Core Features & Use Cases

  • Execute MCP operations via Gemini CLI to preserve context budget.
  • Fall back to the mcp-manager subagent to discover and execute tools when Gemini is unavailable.
  • Do not create any new scripts; rely on existing tooling and defined workflows.

Quick Start

Provide your task as input and run the Gemini CLI with automatic approval to execute MCP operations.

Frequently Asked Questions about ck:use-mcp

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

FAQPage Schema
How do I automate MCP tool discovery and execution inside Gemini CLI?

Automate MCP tool discovery by providing your task as input to run Gemini CLI with automatic approval, utilizing stdin piping for deterministic execution and auto-loaded GEMINI.md to ensure structured JSON-only responses.

What is the fallback mechanism for MCP operations when Gemini CLI is unavailable?

When Gemini is unavailable, MCP operations fall back to the mcp-manager subagent to manually discover and execute tools, preserving context and reducing manual steps while completing the required task execution workflow.

Can I execute MCP tasks using stdin piping with Gemini CLI without writing new scripts?

Yes, you can execute MCP tasks via stdin piping with Gemini CLI without creating new scripts, relying entirely on existing tooling and defined workflows to output a structured JSON result.

How do I get structured JSON-only responses from MCP subagents?

Get structured JSON-only responses by leveraging an auto-loaded GEMINI.md file during Gemini CLI execution, which enforces strict output formatting for your MCP subagent task results.

Does this MCP automation approach preserve the context budget of the subagent?

Yes, executing MCP operations directly via Gemini CLI preserves your context budget by minimizing manual orchestration steps and relying on deterministic task execution workflows.