Track MCP LogoTrack MCP
Track MCP LogoTrack MCP

The world's largest repository of Model Context Protocol servers. Discover, explore, and submit MCP tools.

Product

  • Categories
  • Top MCP
  • New & Updated
  • Submit MCP

Company

  • About

Legal

  • Privacy Policy
  • Terms of Service
  • Cookie Policy

© 2026 TrackMCP. All rights reserved.

Built with ❤️ by Krishna Goyal

    Askme Cli

    An MCP (Model Context Protocol) server that provides user confirmation interface for AI assistants

    4 stars
    TypeScript
    Updated Jun 27, 2025
    mcp-server

    Table of Contents

    • Why
    • How to start
    • Quick Setup with npx
    • Configure MCP Client
    • Cursor (.cursor/mcp_servers.json)
    • Other MCP Clients
    • Local Development
    • How to use
    • Terminal Support
    • API Reference
    • ask_me Tool
    • Usage Examples
    • AI Assistant Integration
    • Example Tool Call
    • Tech Stack
    • License

    Table of Contents

    • Why
    • How to start
    • Quick Setup with npx
    • Configure MCP Client
    • Cursor (.cursor/mcp_servers.json)
    • Other MCP Clients
    • Local Development
    • How to use
    • Terminal Support
    • API Reference
    • ask_me Tool
    • Usage Examples
    • AI Assistant Integration
    • Example Tool Call
    • Tech Stack
    • License

    Documentation

    [!NOTE]

    We'd love your help! If you try askme-cli on Windows or have compatibility fixes, PRs are very welcome👏.

    npm

    GitHub license

    GitHub stars

    npm downloads

    An MCP (Model Context Protocol) server that provides user confirmation interface for AI assistants

    简体中文 | 日本語

    Why

    AI assistants often need user confirmation or next steps, but there's no simple way to get user input during MCP conversations.

    This project provides a personal confirmation endpoint via terminal interface.

    How to start

    You will need to configure your MCP client to use ASKME-CLI.

    Deploy the configuration using the instructions below.

    Quick Setup with npx

    bash
    # View help and configuration examples
    npx askme-cli help
    
    # Run directly (when called by MCP client)
    npx askme-cli

    Configure MCP Client

    Add to your MCP client configuration file:

    Cursor (.cursor/mcp_servers.json)

    json
    {
      "mcpServers": {
        "askme-cli": {
          "command": "npx",
          "args": ["askme-cli"],
          "env": {
            "ASKME_CLI_TERMINAL": "warp"
          }
        }
      }
    }

    Other MCP Clients

    json
    {
      "mcpServers": {
        "askme-cli": {
          "command": "npx",
          "args": ["askme-cli"],
          "env": {
            "ASKME_CLI_TERMINAL": "iterm2"
          }
        }
      }
    }

    Local Development

    bash
    # Clone and install
    git clone 
    cd askme-cli
    npm install
    
    # Build and run
    npm run build
    npm run start

    How to use

    Once configured, the AI assistant can use the ask_me tool to collect user confirmation:

    1. AI assistant calls ask_me tool with summary of completed work

    2. ASKME-CLI opens a new terminal window with confirmation interface

    3. User enters next plan or confirmation and submits

    4. AI assistant receives user input to continue

    Terminal Support

    Configure via ASKME_CLI_TERMINAL environment variable:

    TerminalValueDescription
    WarpwarpDefault, modern terminal app
    iTerm2iterm2Popular macOS terminal
    TerminalterminalmacOS system terminal
    KittykittyCross-platform terminal
    AlacrittyalacrittyGPU-accelerated terminal
    HyperhyperWeb-based terminal

    API Reference

    ask_me Tool

    Collects user's next plan or confirmation.

    Parameters:

    • what_we_did (string): Summary of work completed by AI

    Returns:

    • User's input for next plan or confirmation
    • Supports text and image input

    Usage Examples

    AI Assistant Integration

    To use ASKME-CLI effectively in your AI assistant, add these rules to your system prompt:

    code
    - Must call the askme-cli.ask_me tool before ending any user prompt every time.
    - All prompts starting with /tk, don't modify code or files, and call the askme-cli.ask_me tool before ending.
    - When you have questions, always call the askme-cli.ask_me tool before ending.
    - If you have ideas for new features or changes, explain them clearly, analyze their feasibility, and ask if I want to proceed.

    Example Tool Call

    json
    {
      "tool": "ask_me",
      "parameters": {
        "what_we_did": "I've completed setting up the database schema and created the user authentication endpoints. The API is now ready for testing."
      }
    }

    Tech Stack

    • TypeScript - Type-safe development
    • React + Ink - Terminal UI framework
    • MCP SDK - Model Context Protocol support
    • Node.js - Runtime environment

    License

    MIT

    Similar MCP

    Based on tags & features

    • MC

      Mcp Open Library

      TypeScript·
      42
    • ME

      Metmuseum Mcp

      TypeScript·
      14
    • MC

      Mcp Ipfs

      TypeScript·
      11
    • LI

      Liveblocks Mcp Server

      TypeScript·
      11

    Trending MCP

    Most active this week

    • PL

      Playwright Mcp

      TypeScript·
      22.1k
    • SE

      Serena

      Python·
      14.5k
    • MC

      Mcp Playwright

      TypeScript·
      4.9k
    • MC

      Mcp Server Cloudflare

      TypeScript·
      3.0k
    View All MCP Servers

    Similar MCP

    Based on tags & features

    • MC

      Mcp Open Library

      TypeScript·
      42
    • ME

      Metmuseum Mcp

      TypeScript·
      14
    • MC

      Mcp Ipfs

      TypeScript·
      11
    • LI

      Liveblocks Mcp Server

      TypeScript·
      11

    Trending MCP

    Most active this week

    • PL

      Playwright Mcp

      TypeScript·
      22.1k
    • SE

      Serena

      Python·
      14.5k
    • MC

      Mcp Playwright

      TypeScript·
      4.9k
    • MC

      Mcp Server Cloudflare

      TypeScript·
      3.0k