mcpField
A
Ask UI

Ask UI

Local
github.com/Box-KillerFiles & Storage3Updated 66w ago
Repository

About Ask UI

Ask UI is an MCP server that lets agents ask users questions through custom interfaces. The README describes its purpose but provides few implementation details.

Key features

  1. 01Custom user interfaces for questions
  2. 02Agent-to-user question flow

Use cases

  1. 01Collecting user input during an agent task
  2. 02Presenting questions through a custom interface

MCP support

It acts as an MCP server, enabling agents to ask users questions through custom user interfaces.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "core-box-killer": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-ask-ui"
      ],
      "env": {
        "MOONSHOT_API_KEY": "<MOONSHOT_API_KEY>",
        "PPIO_API_KEY": "<PPIO_API_KEY>",
        "MINIMAX_API_KEY": "<MINIMAX_API_KEY>"
      }
    }
  }
}
Run commandnpx -y mcp-ask-ui
Environment variables to set
MOONSHOT_API_KEYSecret
PPIO_API_KEYSecret
MINIMAX_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-ask-ui

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
promptstringYes
titlestringNo
heightnumberYes

Details

From the project README

mcp-ask-ui

A MCP server that enables agents to ask users questions via custom user interfaces.

Server Config

{
  "mcpServers": {
    "ask-ui": {
      "command": "npx",
      "args": ["-y", "mcp-ask-ui"],
      "env": {
        "MOONSHOT_API_KEY": "all keys are optional",
        "PPIO_API_KEY": "all keys are optional",
        "MINIMAX_API_KEY": "all keys are optional"
      }
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.