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 est le gestionnaire de tâches IA des fondateurs solos et des petites équipes.
La référence des outils est maintenue en anglais : les noms d’outils, les arguments et les exemples sont identiques dans toutes les langues.
Arguments
| Nom | Type | Obligatoire | Description |
|---|---|---|---|
| id | string | oui | Task ID |
| runId | string | oui | The runId returned by start_task |
| leaseToken | string | oui | The leaseToken returned by start_task |
| question | string | oui | One sentence a person can answer (≤500 chars) |
| options | { value, label }[] | non | The alternatives, when there are any. A question with options gets read; a yes/no gets rubber-stamped. |
| urgency | 'blocking' | 'soon' | non | Default 'blocking' |
| holdSeconds | number | non | How long to wait inside the call before parking (default 120, max 240) |
Retour
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.
Annotations
- idempotent. Appeler l’outil deux fois avec les mêmes arguments produit le même effet qu’un seul appel.
Exemple
Ce que dit l’utilisateur :
"Ask me before you send anything to a customer."Ce que l’IA appelle en coulisses :
{
"name": "request_input",
"arguments": {
"id": "…",
"runId": "…",
"leaseToken": "…",
"question": "Which discount should the email offer?",
"options": [
{
"value": "10",
"label": "10%"
},
{
"value": "15",
"label": "15%"
}
]
}
}À voir aussi
- Les 32 outils MCP — la vue catalogue.
- Shuttle — comment le client IA se sert de ces outils.
- Appelez cet outil depuis votre propre client : voir les guides d’installation, ou visez directement
https://letsweft.com/api/mcp.