AskMeMCP
Enables AI assistants to request human input through a web interface, facilitating human-in-the-loop interactions.
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:
-
Auto-discovery (default): Finds available port starting from 3000
npx --yes ask-me-mcp -
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:
-
Enable Debug Mode: Run with debug logging to see what's happening:
ASK_ME_MCP_DEBUG=1 claude --debug -
Check the Server: Test if the server runs correctly:
npx --yes ask-me-mcp --help -
Port Conflicts: If port 3000 is in use, specify a different port:
claude mcp add ask-me npx --yes ask-me-mcp --port 8080 -
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-mcpmay ask for confirmation. Usenpx --yesto 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
Related Servers
Apex X (Twitter) Management
Manage your X (Twitter) account using the Apex social media infrastructure. Requires an Apex API Key.
Windows Notification Server
Allows AI assistants to send native Windows system notifications.
WasenderAPI MCP
Connect WasenderAPI to AI agents and automation tools using the Model Context Protocol. This remote MCP server exposes WhatsApp session management, messaging, contacts, and groups as callable tools for MCP-compatible platforms
Mac Messages MCP
A Python bridge for interacting with the macOS Messages app.
Facebook Ads
MCP server acting as an interface to the Facebook Ads, enabling programmatic access to Facebook Ads data and management features.
LINE Official Account
Integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
Email Processing
An email processing server that uses MongoDB for semantic search and SQLite for efficient storage and retrieval.
ELEMENT.FM
Create and publish unlimited podcast shows and episodes with ELEMENT.FM
Prompt for User Input MCP Server
Enables AI models to prompt users for input directly within their code editor for interactive conversations.
Python LINE MCP Server
An MCP server for accessing and interacting with LINE Bot messages.