Interact MCP

An interactive MCP (Model Context Protocol) server that enables real-time communication between AI assistants and users through a web-based chat interface.

This project provides an MCP server with aninteracttool that allows AI assistants to:

- Ask questions and receive responses from users
- Request confirmation for actions
- Seek guidance or clarification
- Share information in real-time

The server features a Gradio-based web interface that provides a chat UI for seamless user interaction.

- Real-time Interaction: Bidirectional communication between AI and users
- Web-based Chat Interface: Clean, modern UI powered by Gradio
- Multiple Transport Options: Supports both stdio and SSE (Server-Sent Events) transport
- Timeout Handling: Automatic timeout protection for user responses
- Chat History: Maintains conversation history during sessions

git clone <repository-url> cd interact-mcp

- Create and activate a virtual environment:

python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate

This will start the server on127.0.0.1:3033and automatically open the chat interface in your browser.

Specify a custom port for the SSE transport.

Use stdio transport for direct MCP communication.
- The web interface will open automatically in your browser
- Wait for AI assistant messages to appear
- Respond to questions or prompts in the text input field
- Your responses will be sent back to the AI assistant through the MCP protocol

To use this MCP server with Cursor IDE, you'll need to configure it in the MCP configuration file.
- Open Cursor IDE and go toCursor Settings > Tools & Integrationsand click "New MCP Server"
- This will open the~/.cursor/mcp.jsonfile for editing
- Add the following configuration:

{ "mcpServers": { "interact": { "command": "path/to/interact-mcp/venv/bin/python3", "args": ["path/to/interact-mcp/server.py", "--stdio"] } } }

- Replacepath/to/interact-mcpwith the actual path to your project directory
- The Gradio UI should open automatically in your browser

The main tool provided by this server allows AI assistants to interact with users.

- message(str): The message to send to the user

- str: The user's response to the message

- Default timeout is 5 minutes (300 seconds)
- Returns timeout message if no response is received

A PyInstaller spec file is included for creating standalone executables:

This will create adist/serverexecutable that includes all necessary dependencies.

- Built withFastMCPframework
- Uses Gradio for the web interface
- Implements threading for concurrent web UI and MCP server operation
- Supports real-time updates with periodic refresh mechanism

Upfirst is an AI phone receptionist for small businesses. Review call transcripts, then fix the greeting, knowledge, and transfer rules from your AI client.