작업 · MCP

Ask the User a Question

request_input is one of the 32 MCP tools in Weft, the AI task manager you run by talking to Claude, Cursor, Codex or ChatGPT through one MCP endpoint. Ask the person something only they can decide, and wait without losing the claim on the task. If they are at their client, a form appears there and the answer comes back inside the same call — the agent carries on in the same context, with the same claim. If they are away, the call returns parked and the question waits in their queue; the answer reaches the agent at its next start_task or get_my_work. For the irreversible and the genuinely ambiguous, not for "may I continue?" — every question spends the same attention budget that limits new work.

Weft는 1인 창업자와 소규모 팀을 위한 AI 작업 관리 도구입니다.

도구 레퍼런스는 영어로 관리합니다. 도구 이름, 인자, 예시는 모든 언어에서 동일합니다.

인자

이름	타입	필수	설명
id	string	예	Task ID
runId	string	예	The runId returned by start_task
leaseToken	string	예	The leaseToken returned by start_task
question	string	예	One sentence a person can answer (≤500 chars)
options	{ value, label }[]	아니요	The alternatives, when there are any. A question with options gets read; a yes/no gets rubber-stamped.
urgency	'blocking' \| 'soon'	아니요	Default 'blocking'
holdSeconds	number	아니요	How long to wait inside the call before parking (default 120, max 240)

반환값

Either answered:true with the answer and the same runId/leaseToken to continue with, or parked:true with a questionId — the claim is kept either way, and a parked question is delivered back through start_task and get_my_work.

주석

멱등. 같은 인자로 두 번 호출해도 한 번 호출한 것과 결과가 같습니다.

예시

사용자가 하는 말:

"Ask me before you send anything to a customer."

AI가 내부에서 호출하는 것:

json

{
  "name": "request_input",
  "arguments": {
    "id": "…",
    "runId": "…",
    "leaseToken": "…",
    "question": "Which discount should the email offer?",
    "options": [
      {
        "value": "10",
        "label": "10%"
      },
      {
        "value": "15",
        "label": "15%"
      }
    ]
  }
}

인자

반환값

주석

예시

관련 항목