User Prompt MCP logo

User Prompt MCP

by nazar256

User Prompt MCP is a Model Context Protocol (MCP) server for Cursor that enables requesting user input during AI model generation. It allows for a more interactive experience by bridging the gap between the AI and the user.

View on GitHub

Last updated: N/A

What is User Prompt MCP?

User Prompt MCP is an MCP server that allows Cursor (or any MCP-compatible client) to request additional input from users during model generation without ending the generation process. It acts as an intermediary, facilitating a more interactive AI experience.

How to use User Prompt MCP?

To use User Prompt MCP with Cursor, install the server using the provided installation script or manual methods. Then, configure Cursor to use the server by adding it to the MCP Servers section in Cursor's settings. Finally, add a global rule to instruct the AI to use the MCP for user prompts.

Key features of User Prompt MCP

  • User Input Prompting

  • Simple GUI

  • Cross-Platform Compatibility

  • Stdio Transport

Use cases of User Prompt MCP

  • Requesting clarification from users during code generation

  • Gathering additional context for AI models

  • Creating interactive AI-assisted workflows

  • Handling ambiguous situations during AI processing

FAQ from User Prompt MCP

What is Model Context Protocol (MCP)?

MCP is a protocol that allows AI models to request additional context or input from external sources during generation.

What platforms does User Prompt MCP support?

User Prompt MCP should work on both Linux and macOS.

How do I install User Prompt MCP?

You can install User Prompt MCP using the installation script, by building from source, or by downloading pre-compiled binaries from the Releases page.

How do I configure the timeout for user input?

You can configure the timeout using the --timeout command-line flag or the USER_PROMPT_TIMEOUT environment variable.

What are the prerequisites for using the GUI functionality?

For GUI functionality, you need zenity on Linux and osascript (built-in) on macOS.