MCP Confirm Server

MCP server for AI-user confirmation and clarification protocol

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You deploy and run an MCP server that facilitates confirmation and clarification between AI assistants and users. It provides structured, interactive dialogs so AI can ask for yes/no confirmations, clarify ambiguous requests, verify understanding, collect user feedback, and tailor dialogs with custom schemas.

How to use

You integrate this MCP server with your AI client to enable confirmation workflows. Use the available tools to prompt users for confirmation before executing actions, to clarify ambiguous requests, and to verify that the AI’s understanding is correct before proceeding. Typical patterns include posing yes/no questions, presenting multiple interpretation options, and collecting user ratings to gauge satisfaction.

In practice, you call the server’s tools from your AI orchestration layer. For example, before a potentially destructive action, you can trigger a confirm_action dialog that presents the action, its impact, and relevant details. When a user request is ambiguous, use clarify_intent to offer concrete interpretations and options. To ensure the AI proceeds correctly, use verify_understanding to confirm key points before moving forward. And when you want to rate the interaction, collect_rating can capture user satisfaction.

How to install

Prerequisites: ensure you have Node.js and npm installed on your system.

Install the MCP server globally so you can run it from any directory.

Install globally:

npm install -g @mako10k/mcp-confirm

Or run it directly with npx without a global install.

npx @mako10k/mcp-confirm

Configuration and runtime notes

You can tailor runtime behavior using environment variables. The server supports a dedicated log for confirmation history and a timeout for confirmations.

Environment variables you can configure include:

• MCP_CONFIRM_LOG_PATH: Path to the confirmation history log file (default: .mcp-data/confirmation_history.log)

• MCP_CONFIRM_TIMEOUT_MS: Default timeout for confirmations in milliseconds (default: 180000, i.e., 3 minutes)

• NODE_ENV: Set to development to enable debug logging

Usage patterns and examples

Basic confirmation uses a simple yes/no flow to confirm a straightforward request.

Intent clarification helps you present multiple plausible interpretations when user requests are ambiguous.

Understanding verification ensures the AI’s interpretation aligns with user intent before taking action.

You can also collect ratings to gauge how well the AI addressed the user’s needs.

Development and testing

The server supports development workflows via Codespaces and local testing. Use the standard npm/yarn/npm run workflows to build and run locally.

Available tools

ask_yes_no

Ask yes/no confirmation questions to clarify whether to proceed with an action.

confirm_action

Confirm actions before execution, including impact and details in the confirmation dialog.

clarify_intent

Clarify ambiguous requests by presenting multiple interpretation options.

verify_understanding

Verify that the AI’s understanding is correct before proceeding to the next steps.

collect_rating

Collect user satisfaction ratings to evaluate AI response quality.

elicit_custom

Provide custom confirmation dialogs using custom JSON schemas.

search_logs

Search confirmation history logs with filters and pagination.

analyze_logs

Perform statistical analysis of confirmation history, including trends and success rates.