Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Ask Question MCP App Ask the user which features they want to include in their new project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP App that provides an interactive UI for asking questions with various input types.
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
npm install
npm run buildThe MCP server exposes a single tool ask_question with the following parameters:
Parameter | Type | Required | Description |
| string | Yes | The question to display |
| enum | Yes |
|
| array | No | Options for select/multiselect (each with |
| string | No | Placeholder text for text input |
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"
}Add to your .vscode/mcp.json:
{
"servers": {
"ask-question-mcp": {
"type": "stdio",
"command": "node",
"args": ["/path/to/ask-question-mcp/dist/index.js"]
}
}
}npm run watchMIT
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.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question to ask the user | |
| inputType | Yes | Type of input: 'text' for free-form input, 'select' for single choice, 'multiselect' for multiple choices, 'confirm' for yes/no | |
| options | No | Options for select/multiselect input types | |
| placeholder | No | Placeholder text for text input | |
| timeout | No | Timeout in milliseconds (default: 5 minutes) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes key behaviors like waiting for user response and returning the answer, and mentions timeout with a default value. However, it lacks details on error handling, UI appearance, or what happens if the user cancels.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with two sentences that are front-loaded with core functionality. It efficiently covers the tool's purpose and key features without unnecessary details, though it could be slightly more structured by separating behavioral aspects.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (5 parameters, interactive UI) and no annotations or output schema, the description is somewhat complete but has gaps. It covers the basic flow and input types but lacks details on return values, error cases, or UI constraints, which could hinder an agent's ability to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no specific parameter semantics beyond what the schema provides, such as explaining how options are displayed or the implications of different input types. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('ask', 'waits', 'returns') and resources ('user', 'question', 'interactive UI'), and distinguishes it from its sibling submit_answer by focusing on initiating queries rather than responding to them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when needing user input via interactive dialogs, but does not explicitly state when to use this tool versus alternatives or provide exclusions. It mentions support for various input types, which gives some contextual guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit an answer to a pending question. Used internally by the question UI.
| Name | Required | Description | Default |
|---|---|---|---|
| questionId | Yes | The ID of the question being answered | |
| answer | Yes | The user answer |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions internal use by the question UI, hinting at context, but lacks details on permissions, side effects, response format, or error handling. For a mutation tool with zero annotation coverage, this is insufficient behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief and front-loaded with the core purpose in the first sentence. The second sentence adds context efficiently. However, it could be more structured by explicitly separating usage from behavior, but overall it avoids unnecessary verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete for a mutation tool. It lacks details on what happens after submission, error scenarios, or interaction with the sibling tool. The internal use hint is insufficient for full contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters fully. The description doesn't add any meaning beyond what the schema provides, such as format examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('submit an answer') and target resource ('to a pending question'), providing a specific verb+resource combination. However, it doesn't differentiate from the sibling tool 'ask_question' beyond mentioning it's used internally by the question UI, which is helpful but not explicit about functional distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal guidance with 'Used internally by the question UI,' which implies a specific context but doesn't offer explicit when-to-use rules, alternatives, or exclusions. No mention of when to use this versus the sibling 'ask_question' tool, leaving gaps in practical usage advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0ask_questionsubmit_answerScored across 2 tools
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.
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.
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.
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.
Generate, inspect, and manage Flowstep UI designs directly from your AI assistant.
Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Create AI surveys with dynamic follow-up probing directly from your AI assistant.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
