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.
Weft je AI správca úloh pre samostatných zakladateľov a malé tímy.
Referenčný popis nástrojov sa udržiava v angličtine: názvy nástrojov, argumenty aj príklady sú vo všetkých jazykoch rovnaké.
Argumenty
| Názov | Typ | Povinný | Popis |
|---|---|---|---|
| id | string | áno | Task ID |
| runId | string | áno | The runId returned by start_task |
| leaseToken | string | áno | The leaseToken returned by start_task |
| question | string | áno | One sentence a person can answer (≤500 chars) |
| options | { value, label }[] | nie | The alternatives, when there are any. A question with options gets read; a yes/no gets rubber-stamped. |
| urgency | 'blocking' | 'soon' | nie | Default 'blocking' |
| holdSeconds | number | nie | How long to wait inside the call before parking (default 120, max 240) |
Vracia
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.
Anotácie
- idempotentný. Zavolať nástroj dvakrát s rovnakými argumentmi má rovnaký účinok ako zavolať ho raz.
Príklad
Čo povie používateľ:
"Ask me before you send anything to a customer."Čo AI pod kapotou zavolá:
{
"name": "request_input",
"arguments": {
"id": "…",
"runId": "…",
"leaseToken": "…",
"question": "Which discount should the email offer?",
"options": [
{
"value": "10",
"label": "10%"
},
{
"value": "15",
"label": "15%"
}
]
}
}Súvisiace
- Všetkých 32 MCP nástrojov — pohľad na katalóg.
- Člnok — ako tieto nástroje používa AI klient.
- Zavolaj tento nástroj zo svojho vlastného klienta: návody na nastavenie, alebo pošli požiadavku priamo na
https://letsweft.com/api/mcp.