$git clone https://github.com/ttommyth/interactive-mcpA MCP Server implemented in Node.js/TypeScript, facilitating interactive communication between LLMs and users. Note: This server is designed to run locally alongside the MCP client (e.g., Claude Desktop, VS Code), as it needs direct access to the user's operating system to di
| 1 | # interactive-mcp |
| 2 | |
| 3 | [](https://www.npmjs.com/package/interactive-mcp) [](https://www.npmjs.com/package/interactive-mcp) [](https://smithery.ai/server/@ttommyth/interactive-mcp) [](https://github.com/ttommyth/interactive-mcp/blob/main/LICENSE) [](https://github.com/prettier/prettier) [](https://github.com/ttommyth/interactive-mcp) [](https://github.com/ttommyth/interactive-mcp/commits/main) |
| 4 | |
| 5 | [](https://cursor.com/install-mcp?name=interactive&config=eyJjb21tYW5kIjoibnB4IC15IGludGVyYWN0aXZlLW1jcCJ9) |
| 6 | |
| 7 |  |
| 8 | |
| 9 | A MCP Server implemented in Node.js/TypeScript, facilitating interactive communication between LLMs and users. **Note:** This server is designed to run locally alongside the MCP client (e.g., Claude Desktop, VS Code), as it needs direct access to the user's operating system to display notifications and command-line prompts. |
| 10 | |
| 11 | _(Note: This project is in its early stages.)_ |
| 12 | |
| 13 | **Want a quick overview?** Check out the introductory blog post: [Stop Your AI Assistant From Guessing — Introducing interactive-mcp](https://medium.com/@ttommyth/stop-your-ai-assistant-from-guessing-introducing-interactive-mcp-b42ac6d9b0e2) |
| 14 | |
| 15 | [Demo Video](https://youtu.be/ebwDZdfgSHo) |
| 16 | |
| 17 | <div align="center"> |
| 18 | <a href="https://glama.ai/mcp/servers/@ttommyth/interactive-mcp"> |
| 19 | <img width="380" height="200" src="https://glama.ai/mcp/servers/@ttommyth/interactive-mcp/badge" alt="interactive-mcp MCP server" /> |
| 20 | </a> |
| 21 | </div> |
| 22 | |
| 23 | ## Tools |
| 24 | |
| 25 | This server exposes the following tools via the Model Context Protocol (MCP): |
| 26 | |
| 27 | - `request_user_input`: Asks the user a question and returns their answer. Can display predefined options. |
| 28 | - `message_complete_notification`: Sends a simple OS notification. |
| 29 | - `start_intensive_chat`: Initiates a persistent command-line chat session. |
| 30 | - `ask_intensive_chat`: Asks a question within an active intensive chat session. |
| 31 | - `stop_intensive_chat`: Closes an active intensive chat session. |
| 32 | |
| 33 | ## Demo |
| 34 | |
| 35 | Here are demonstrations of the interactive features: |
| 36 | |
| 37 | | Normal Question | Completion Notification | |
| 38 | | :--------------------------------------------------------: | :-----------------------------------------------------------------: | |
| 39 | |  |  | |
| 40 | |
| 41 | | Intensive Chat Start | Intensive Chat End | |
| 42 | | :------------------------------------------------------------------: | :--------------------------------------------------------------: | |
| 43 | |  |  | |
| 44 | |
| 45 | ## Usage Scenarios |
| 46 | |
| 47 | This server is ideal for scenarios where an LLM needs to interact directly with the user on their local machine, such as: |
| 48 | |
| 49 | - Interactive setup or configuration processes. |
| 50 | - Gathering feedback during code generation or modification. |
| 51 | - Clarifying instructions or confirming actions in pair programming. |
| 52 | - Any workflow requiring user input or confirmation during LLM operation. |
| 53 | |
| 54 | ## Client Configuration |
| 55 | |
| 56 | This section explains how to configure MCP clients to use the `inte |