Skip to main content
Glama

MCP-Confirm

by mako10k

@mako10k/mcp-confirm

AI-ユーザー間の復唱確認プロトコルを実装するMCPサーバーです。LLMが不安になったときに、ユーザーに確認を取るためのツールを提供します。

@mako10k/mcp-confirm

A Model Context Protocol (MCP) server for AI-user confirmation and clarification. This server provides tools for AI assistants (LLMs) to ask users for confirmation when they need clarification or verification.

Overview

This MCP server implements the Model Context Protocol Elicitation specification to enable confirmation and clarification protocols between AI assistants and users.

AI assistants can use this in situations such as:

  • Confirming actions before execution
  • Clarifying ambiguous requests
  • Verifying understanding is correct
  • Asking yes/no questions
  • Collecting user satisfaction ratings

Features

Available Tools

  1. ask_yes_no
    • Ask yes/no confirmation questions
    • Used when AI needs clarification or verification
  2. confirm_action
    • Confirm actions before execution
    • Includes impact and details in confirmation dialog
  3. clarify_intent
    • Clarify ambiguous requests
    • Present multiple interpretation options
  4. verify_understanding
    • Verify AI's understanding is correct
    • Confirm next steps before proceeding
  5. collect_rating
    • Collect user satisfaction ratings
    • Evaluate AI response quality
  6. elicit_custom
    • Custom confirmation dialogs
    • Use custom JSON schemas
  7. search_logs
    • Search confirmation history logs
    • Filter by type, success status, date range, response time
    • Paginated results for large datasets
  8. analyze_logs
    • Statistical analysis of confirmation history
    • Success rates, response times, trends
    • Grouping by type, time period, etc.

Installation

# Install globally npm install -g @mako10k/mcp-confirm # Or use with npx npx @mako10k/mcp-confirm

Configuration

Environment Variables

You can configure the server using environment variables:

  • MCP_CONFIRM_LOG_PATH: Path to confirmation history log file (default: .mcp-data/confirmation_history.log)
  • MCP_CONFIRM_TIMEOUT_MS: Default timeout for confirmations in milliseconds (default: 60000)
  • NODE_ENV: Set to development to enable debug logging

Timeout Behavior

The server uses intelligent timeout settings based on confirmation type:

  • Critical actions (delete, remove operations): 120 seconds
  • Warning actions: 90 seconds
  • Simple yes/no questions: 30 seconds
  • Rating requests: 20 seconds (reference only)
  • Other confirmations: 60 seconds (default)

Confirmation History Logging

All confirmation interactions are logged to a file for audit purposes. The log includes:

  • Timestamp of the request
  • Confirmation type
  • Full request and response data
  • Response time in milliseconds
  • Success/failure status
  • Error messages (if any)

The log directory (.mcp-data/) will be created automatically if it doesn't exist.

VS Code Integration

Add to your .vscode/mcp.json:

{ "servers": { "mcp-confirm": { "type": "stdio", "command": "npx", "args": ["@mako10k/mcp-confirm"] } } }

Claude Desktop Configuration

Add to your Claude Desktop config.json:

Windows

Location: %APPDATA%\Claude\config.json

macOS

Location: ~/Library/Application Support/Claude/config.json

Linux

Location: ~/.config/claude/config.json

{ "mcp": { "servers": { "mcp-confirm": { "command": "npx", "args": ["@mako10k/mcp-confirm"], "env": { "MCP_CONFIRM_LOG_PATH": "~/.mcp-data/confirmation_history.log", "MCP_CONFIRM_TIMEOUT_MS": "60000", "NODE_ENV": "production" } } } } }

Usage Examples

Basic Confirmation

// Before AI executes an action await confirm_action({ action: "Delete files", impact: "Cannot be restored", details: "10 files will be deleted" });

Intent Clarification

// When request is ambiguous await clarify_intent({ request_summary: "Want to create a project", ambiguity: "Type of project unclear", options: ["Node.js project", "Python project", "React app"] });

Understanding Verification

// Before complex tasks await verify_understanding({ understanding: "Create web application with user authentication", key_points: ["React + Node.js", "JWT authentication", "PostgreSQL database"], next_steps: "Create project structure then implement auth system" });

Technical Specifications

  • Protocol: Model Context Protocol Elicitation
  • Language: TypeScript
  • Runtime: Node.js
  • SDK Version: @modelcontextprotocol/sdk ^1.0.0

How It Works

This server implements true MCP Elicitation protocol:

  1. Sends elicitation/create method to client
  2. Defines user input structure with JSON Schema
  3. User responds with accept, decline, or cancel
  4. On accept, receives structured data following schema

This enables reliable communication between AI and users.

Development

# Clone repository git clone https://github.com/mako10k/mcp-confirm.git cd mcp-confirm # Install dependencies npm install # Build npm run build # Run locally npm start # Quality checks npm run quality

License

MIT License - see LICENSE file for details.

Repository

機能

利用可能なツール

  1. ask_yes_no
    • はい/いいえの確認質問
    • AIが明確化や検証が必要な時に使用
  2. confirm_action
    • アクション実行前の確認
    • 影響や詳細を含めた確認ダイアログ
  3. clarify_intent
    • あいまいなリクエストの意図確認
    • 複数の解釈オプションの提示
  4. verify_understanding
    • AIの理解が正しいかの検証
    • 次のステップの確認
  5. collect_rating
    • ユーザー満足度の収集
    • AIの回答品質の評価
  6. elicit_custom
    • カスタム確認ダイアログ
    • 独自のJSONスキーマを使用

セットアップ

# 依存関係のインストール npm install # ビルド npm run build # 実行(グローバルインストール後) npm install -g @mako10k/mcp-confirm mcp-confirm # または npx で直接実行 npx @mako10k/mcp-confirm

VS Code統合

.vscode/mcp.jsonでMCPクライアントとして設定済み:

{ "servers": { "mcp-confirm": { "type": "stdio", "command": "npx", "args": ["@mako10k/mcp-confirm"] } } }

使用例

基本的な確認

// AIがアクションを実行する前 await confirm_action({ action: "ファイルを削除", impact: "復元できません", details: "10個のファイルが削除されます" });

意図の確認

// あいまいなリクエストの場合 await clarify_intent({ request_summary: "プロジェクトを作成したい", ambiguity: "どの種類のプロジェクトか不明", options: ["Node.js プロジェクト", "Python プロジェクト", "React アプリ"] });

理解の検証

// 複雑なタスクの前 await verify_understanding({ understanding: "Webアプリケーションを作成して、ユーザー認証を実装する", key_points: ["React + Node.js", "JWT認証", "PostgreSQLデータベース"], next_steps: "プロジェクト構造を作成してから認証システムを実装" });

技術仕様

  • プロトコル: Model Context Protocol Elicitation
  • 言語: TypeScript
  • ランタイム: Node.js
  • SDKバージョン: @modelcontextprotocol/sdk ^1.0.0

プロトコルの仕組み

このサーバーは真のMCP Elicitationプロトコルを実装しており:

  1. elicitation/createメソッドでクライアントにリクエスト送信
  2. JSONスキーマでユーザー入力の構造を定義
  3. ユーザーはacceptdeclinecancelで応答
  4. acceptの場合、スキーマに従った構造化データを受信

これにより、AIとユーザー間の確実な意思疎通が可能になります。

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

An MCP server implementing AI-user confirmation protocols, providing tools for LLMs to seek user confirmation when uncertain through yes/no questions, action confirmations, intent clarification, understanding verification, and satisfaction ratings.

  1. @mako10k/mcp-confirm
    1. Overview
    2. Features
    3. Installation
    4. Configuration
    5. Usage Examples
    6. Technical Specifications
    7. How It Works
    8. Development
    9. License
    10. Repository
    11. 機能
    12. セットアップ
    13. VS Code統合
    14. 使用例
    15. 技術仕様
    16. プロトコルの仕組み

Related MCP Servers

  • A
    security
    A
    license
    A
    quality
    A Model Context Protocol server that enables AI assistants to interact with Linear project management systems, allowing users to retrieve, create, and update issues, projects, and teams through natural language.
    Last updated -
    32
    765
    94
    TypeScript
    MIT License
    • Apple
  • -
    security
    A
    license
    -
    quality
    An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.
    Last updated -
    Python
    MIT License
  • -
    security
    F
    license
    -
    quality
    A specialized server that enables LLMs to gather specific information through sequential questioning, implementing the MCP standard for seamless integration with LLM clients.
    Last updated -
    1
    Python
  • A
    security
    A
    license
    A
    quality
    A Node.js/TypeScript MCP server that facilitates interactive communication between LLMs and users, allowing AI assistants to request user input, display notifications, and manage command-line chat sessions.
    Last updated -
    5
    485
    TypeScript
    MIT License
    • Apple
    • Linux

View all related MCP servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mako10k/mcp-confirm'

If you have feedback or need assistance with the MCP directory API, please join our Discord server