Ask User Questions MCP Server

MCPOpen SourceMIT57.6

by paulp-o • Uncategorized

An MCP server tool enabling AI assistants to ask clarifying questions via a separate CLI interface.

Example Use Cases

1
Ask clarifying questions during long-running autonomous workflows.
2
Multi-agent interoperability and question queueing support.
3
A non-invasive, terminal-based human-in-the-loop interface.

Description

This MCP server allows AI agents to ask single or multiple choice clarifying questions with options for custom input, rejection, and elaboration. It supports multi-agent workflows, multiple renderers, native OS notifications, and multi-language support, enhancing human-in-the-loop interaction in long-running AI tasks. The tool integrates flexibly with various AI environments like Claude Code, Cursor, and OpenCode, and can be used remotely via SSH without disrupting workflows.

Capabilities(2 total)

Tools (2)

ask_user_questions

Use this tool when you need to ask the user questions during execution. This allows you to: Gather user preferences or requirements Clarify ambiguous instructions Get decisions on implementation choices as you work Offer choices to the user about what direction to take. Usage notes: Users will always be able to select "Other" to provide custom text input Use multiSelect: true to allow multiple answers to be selected for a question Recommend an option unless absolutely necessary, make it the first option in the list and add "(Recommended)" at the end of the label For multiSelect questions, you MAY mark multiple options as "(Recommended)" if several choices are advisable Do NOT use this tool to ask "Is my plan ready?" or "Should I proceed?"

questions:array*nonBlocking:boolean

get_answered_questions

Fetch answers for a previously submitted non-blocking question set. Use this after calling ask_user_questions with nonBlocking: true. Returns the user's answers if available, or current session status if still pending.

session_id:string*blocking:boolean

Quick Actions

View on GitHub

Security

Scanned 1 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C63/100

11/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities2 Tools / 0 Prompts / 0 Resources

Ownerpaulp-o

CategoryUncategorized

DependenciesStandalone

Set Your Username