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 is het AI-takenbeheer voor solo-oprichters en kleine teams.
De toolreferentie wordt in het Engels onderhouden: toolnamen, argumenten en voorbeelden zijn in elke taal identiek.
Argumenten
| Naam | Type | Verplicht | Beschrijving |
|---|---|---|---|
| id | string | ja | Task ID |
| runId | string | ja | The runId returned by start_task |
| leaseToken | string | ja | The leaseToken returned by start_task |
| question | string | ja | One sentence a person can answer (≤500 chars) |
| options | { value, label }[] | nee | The alternatives, when there are any. A question with options gets read; a yes/no gets rubber-stamped. |
| urgency | 'blocking' | 'soon' | nee | Default 'blocking' |
| holdSeconds | number | nee | How long to wait inside the call before parking (default 120, max 240) |
Retourneert
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.
Annotaties
- idempotent. De tool twee keer met dezelfde argumenten aanroepen heeft hetzelfde effect als één keer.
Voorbeeld
Wat de gebruiker zegt:
"Ask me before you send anything to a customer."Wat de AI eronder aanroept:
{
"name": "request_input",
"arguments": {
"id": "…",
"runId": "…",
"leaseToken": "…",
"question": "Which discount should the email offer?",
"options": [
{
"value": "10",
"label": "10%"
},
{
"value": "15",
"label": "15%"
}
]
}
}Verwant
- Alle 32 MCP-tools — het catalogusoverzicht.
- Schietspoel — hoe de AI-client deze tools gebruikt.
- Roep deze tool aan vanuit je eigen client: bekijk de installatiegidsen, of spreek
https://letsweft.com/api/mcprechtstreeks aan.