AskMeMCP

AskMeMCP

Enables AI assistants to request human input through a web interface, allowing them to pause execution and wait for responses via interactive tools like single questions, multiple choice selections, hypothesis challenges, and decision workflows.

Category
Visit Server

README

AskMeMCP - Human-in-the-Loop MCP Server

AskMeMCP is a Model Context Protocol (MCP) server that enables AI assistants to request human input through a web interface. It implements multiple interactive tools (ask-one-question, ask-multiple-choice, challenge-hypothesis, choose-next), allowing MCP clients like Claude Code to pause execution and wait for human responses.

Features

  • stdio Transport: Direct integration with Claude Code and other MCP clients
  • Self-Contained Server: Serves Angular UI statically - no separate UI server needed
  • Dynamic Port Allocation: Automatically finds available port if default is in use
  • Automatic Browser Opening: Opens UI automatically when requests arrive
  • Real-time Updates: Server-Sent Events for live communication
  • Multiple Tool Types: Single questions, multiple choice, hypothesis challenges, and decision workflows

Installation

Option 1: Using npx (No Installation Required)

You can run Ask-Me MCP directly using npx without installing it globally:

npx ask-me-mcp

Note: The first time you run this, npx will ask for confirmation to install the package temporarily. To skip this confirmation, use:

npx --yes ask-me-mcp

Option 2: Global Installation

npm install -g ask-me-mcp
ask-me-mcp

Configuration for Different Clients

Claude Desktop App

Add to your Claude configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ask-me": {
      "command": "npx",
      "args": ["--yes", "ask-me-mcp"]
    }
  }
}

Claude Code

Using the CLI:

claude mcp add askme -- npx -y ask-me-mcp

Or manually add to your Claude Code configuration:

  • macOS: ~/Library/Application Support/Claude/claude_code_config.json
  • Windows: %APPDATA%\Claude\claude_code_config.json
  • Linux: ~/.config/Claude/claude_code_config.json
{
  "mcpServers": {
    "ask-me": {
      "command": "npx",
      "args": ["--yes", "ask-me-mcp"]
    }
  }
}

Cursor

Add to your Cursor settings (in .cursor/mcp_settings.json in your project root):

{
  "mcpServers": {
    "ask-me": {
      "command": "npx",
      "args": ["--yes", "ask-me-mcp"]
    }
  }
}

VS Code with Continue or Similar Extensions

For VS Code extensions that support MCP, add to your extension's configuration:

{
  "mcpServers": {
    "ask-me": {
      "command": "npx",
      "args": ["--yes", "ask-me-mcp"]
    }
  }
}

Port Configuration

The server has two port behaviors:

  1. Auto-discovery (default): Finds available port starting from 3000

    npx --yes ask-me-mcp
    
  2. Fixed port: Uses exact port specified with --port (fails if port is in use)

    npx --yes ask-me-mcp --port 8080
    

For Claude Code configuration with fixed port:

{
  "mcpServers": {
    "ask-me": {
      "command": "npx",
      "args": ["--yes", "ask-me-mcp", "--port", "8080"]
    }
  }
}

Option 3: Build from Source

# Clone the repository
git clone https://github.com/yourusername/AskMeMCP.git
cd AskMeMCP

# Install dependencies
npm install

# Build all projects
npm run build

# Configure Claude Code with full path

Add to your Claude Code configuration:

{
  "mcpServers": {
    "ask-me": {
      "command": "node",
      "args": ["/full/path/to/AskMeMCP/dist/askme-server/main.js"]
    }
  }
}

Usage

Once configured, you can use the available tools in Claude Code:

ask-one-question Tool

Please use the ask-one-question tool to ask me what my favorite color is

ask-multiple-choice Tool

Please use the ask-multiple-choice tool with these questions:
{
  "questions": [
    {
      "text": "Which deployment environments should we target?",
      "options": ["Development", "Staging", "Production"]
    },
    {
      "text": "Which features should be included in this release?",
      "options": ["User Authentication", "Dashboard Updates", "API Improvements", "Mobile Support"]
    }
  ]
}

All requests will appear in the web UI where you can provide responses. For multiple choice questions, you can select multiple options and add comments to each choice.

Architecture

  • askme-server: stdio MCP server with embedded HTTP bridge for browser communication
  • askme-ui: Angular 20+ frontend with reactive UI using signals
  • askme-shared: Shared TypeScript types for frontend-backend communication

Development

# Run the UI in development mode
npx nx serve askme-ui

# Run the server in development mode
npx nx serve askme-server

# Run tests
npx nx test askme-ui
npx nx test askme-server

# Lint code
npx nx lint askme-ui
npx nx lint askme-server

Troubleshooting

Connection Issues with Claude Code

If you see "Connection failed" errors:

  1. Enable Debug Mode: Run with debug logging to see what's happening:

    ASK_ME_MCP_DEBUG=1 claude --debug
    
  2. Check the Server: Test if the server runs correctly:

    npx --yes ask-me-mcp --help
    
  3. Port Conflicts: If port 3000 is in use, specify a different port:

    claude mcp add ask-me npx --yes ask-me-mcp --port 8080
    
  4. Manual Test: Run the server directly to see any errors:

    npx --yes ask-me-mcp
    

Common Issues

  • First Time Confirmation: The first run of npx ask-me-mcp may ask for confirmation. Use npx --yes to skip this.
  • Port Already in Use: The server automatically finds an available port, but you can specify one with --port
  • Browser Not Opening: If the browser doesn't open automatically, manually navigate to the port shown in debug logs

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured