Skip to main content
Glama
Ask Question MCP App

Ask Question MCP App

Ask Question MCP App

An MCP App that provides an interactive UI for asking questions with various input types.

Features

  • Text Input: Free-form text area for open-ended questions

  • Single Select: Choose one option from a list

  • Multi-Select: Choose multiple options with checkboxes

  • Confirm: Simple Yes/No confirmation dialog

Related MCP server: AskMeMCP

Installation

npm install
npm run build

Usage

The MCP server exposes a single tool ask_question with the following parameters:

Parameter

Type

Required

Description

question

string

Yes

The question to display

inputType

enum

Yes

text, select, multiselect, or confirm

options

array

No

Options for select/multiselect (each with value, label, optional description)

placeholder

string

No

Placeholder text for text input

Examples

Text Input:

{
	"question": "What feature would you like to implement?",
	"inputType": "text",
	"placeholder": "Describe the feature..."
}

Single Select:

{
	"question": "Which framework do you prefer?",
	"inputType": "select",
	"options": [
		{
			"value": "react",
			"label": "React",
			"description": "A JavaScript library for building user interfaces"
		},
		{
			"value": "vue",
			"label": "Vue",
			"description": "The progressive JavaScript framework"
		},
		{
			"value": "svelte",
			"label": "Svelte",
			"description": "Cybernetically enhanced web apps"
		}
	]
}

Multi-Select:

{
	"question": "Select the features to include:",
	"inputType": "multiselect",
	"options": [
		{ "value": "auth", "label": "Authentication" },
		{ "value": "db", "label": "Database" },
		{ "value": "api", "label": "REST API" },
		{ "value": "tests", "label": "Unit Tests" }
	]
}

Confirmation:

{
	"question": "Do you want to proceed with the deployment?",
	"inputType": "confirm"
}

VS Code Configuration

Add to your .vscode/mcp.json:

{
	"servers": {
		"ask-question-mcp": {
			"type": "stdio",
			"command": "node",
			"args": ["/path/to/ask-question-mcp/dist/index.js"]
		}
	}
}

Development

npm run watch

License

MIT

Available Tools

2 tools
ask_questionA

Ask the user a question with an interactive UI. Supports text input, single/multi-select options, and yes/no confirmation dialogs. Waits for user response and returns the answer.

Inputs: question (required), inputType (required), options, placeholder, +1 more.

submit_answerC

Submit an answer to a pending question. Used internally by the question UI.

Inputs: questionId (required), answer (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: ask_question initiates a question to the user with UI support, while submit_answer handles the response submission. There is no overlap or ambiguity between them, as one is for asking and the other for answering.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (ask_question and submit_answer), using snake_case throughout. The naming is predictable and aligns well with their functions, with no deviations or mixed conventions.

    Tool Count2/5

    With only 2 tools, the set feels thin for a server named 'Ask Question MCP App', which suggests a broader interactive questioning domain. This minimal count may limit functionality, as agents might expect more features like managing questions or handling different dialog types beyond the basic ask-answer cycle.

    Completeness2/5

    The tool surface is significantly incomplete for an interactive questioning domain. While ask_question and submit_answer cover a basic ask-answer flow, there are notable gaps such as tools for listing pending questions, canceling questions, or handling different UI modes beyond the described ones. This could lead to agent failures in more complex scenarios.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to request human input through a web interface, allowing them to pause execution and wait for responses via interactive tools like single questions, multiple choice selections, hypothesis challenges, and decision workflows.
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to request human input through a web interface during execution. Supports single questions, multiple choice selections, hypothesis challenges, and decision workflows for human-in-the-loop interactions.
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to request human input through interactive GUI dialogs with quiz-style questions, supporting multiple choice and free-form responses for clarification, decisions, and knowledge extraction.
      1
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to ask clarification questions and receive structured user input through a Human-in-the-Loop interface.
      1
      MIT

    Appeared in Searches