User Prompt Interactive
STDIOMCP server that enables requesting user input during AI model generation.
MCP server that enables requesting user input during AI model generation.
A Model Context Protocol (MCP) server for Cursor that enables requesting user input during generation. This is mostly AI-generated code.
This project implements 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 serves as a bridge between the AI model and the user, creating a more interactive experience.
The easiest way to install user-prompt-mcp is using our installation script, which automatically downloads the appropriate binary for your system:
# Install the latest version curl -sSL https://raw.githubusercontent.com/nazar256/user-prompt-mcp/main/install.sh | bash # Or install a specific version curl -sSL https://raw.githubusercontent.com/nazar256/user-prompt-mcp/main/install.sh | bash -s -- -v v1.0.0
The installation script will:
If you prefer to build from source (requires Go 1.18+):
go install github.com/nazar256/user-prompt-mcp/cmd/user-prompt-mcp@latest
You can also download pre-compiled binaries directly from the Releases page.
{ "mcpServers": { "prompt": { "command": "user-prompt-mcp" } } }
Save and refresh
Add to global rules something like: "Important - do not finish responding until explicitly told to do so, instead always use MCP input_user_prompt
and wait for response in all cases, either you feel stuck, you have question or you finished work on a prompt - always communicate with the user using this MCP."
The server can be configured using command-line flags or environment variables:
By default, the server will wait 20 minutes for user input before timing out. You can customize this timeout using:
--timeout <seconds>
user-prompt-mcp --timeout 600 # Set timeout to 10 minutes
USER_PROMPT_TIMEOUT=<seconds>
export USER_PROMPT_TIMEOUT=1800 # Set timeout to 30 minutes user-prompt-mcp
Now when using Cursor, the AI can request additional input from you without ending its generation.
MIT