use-mcp

name	use-mcp
version	1.0.0
description	[AI & Tools] Use when working with Model Context Protocol (MCP) server tools.
disable-model-invocation	false

Quick Summary

Goal: Utilize MCP (Model Context Protocol) server tools to extend Claude's capabilities.

Workflow:

1. Discover -- List available MCP tools and their capabilities
2. Select -- Choose appropriate tool for the task
3. Execute -- Run MCP tool with correct parameters

Key Rules:

• Check available MCP servers before attempting to use tools
• Use MCP tools for capabilities not available in built-in tools
• Handle MCP tool errors gracefully with fallback approaches

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Execute MCP operations via Gemini CLI to preserve context budget.

Execution Steps

1. Execute task via Gemini CLI (using stdin pipe for MCP support):

   # IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)
   echo "$ARGUMENTS. Return JSON only per GEMINI.md instructions." | gemini -y -m gemini-2.5-flash
   

2. Fallback to general-purpose subagent (if Gemini CLI unavailable):

   • Use general-purpose subagent to discover and execute tools
   • If the subagent got issues with the scripts of mcp-management skill, use mcp-builder skill to fix them
   • DO NOT create ANY new scripts
   • The subagent can only use MCP tools if any to achieve this task
   • If the subagent can't find any suitable tools, just report it back to the main agent to move on to the next step

Important Notes

• MUST ATTENTION use stdin piping - the deprecated -p flag skips MCP initialization
• Use -y flag to auto-approve tool execution
• GEMINI.md auto-loaded: Gemini CLI automatically loads GEMINI.md from project root, enforcing JSON-only response format
• Parseable output: Responses are structured JSON: {"server":"name","tool":"name","success":true,"result":<data>,"error":null}

Anti-Pattern (DO NOT USE)

# BROKEN - deprecated -p flag skips MCP server connections!
gemini -y -m gemini-2.5-flash -p "..."

---

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.