POST/api/v1/meetings/ask

Ask across meetings

Asks a question about every meeting in a workspace you can open, as Server-Sent Events: status, results (the meetings used, best first), delta (the answer as it's written), then done with the answer and its citations (label, kind: segment or page, text like "Ada Lovelace, 12:34", and href), or limit / error. Claude Haiku 5.5 answers in English; each cited meeting is checked against your access again. Counts towards Meetings AI.

API token required30 per minute per IPMCP: ask_meetings

Guide: Meetings

Code samples and Try it

Request body

application/json, required

workspacestringRequired
File it in this workspace: the workspace's id. Up to 40 characters.
questionstringRequired
1–600 characters.

Responses

200OK.
401No token, or the token is revoked or mistyped.
422The request didn't validate. detail lists each problem, with where it is (loc) and why (msg).
429Too many requests from your IP address. Wait the seconds in Retry-After.

curl -X POST https://api.markdrop.in/api/v1/meetings/ask \ -H "Authorization: Bearer $MARKDROP_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "workspace": "665f1c2ab3e4d5f6a7b8c9d0", "question": "What did we decide about pricing?" }'

const res = await fetch("https://api.markdrop.in/api/v1/meetings/ask", { method: "POST", headers: { Authorization: `Bearer ${process.env.MARKDROP_TOKEN}`, "Content-Type": "application/json", }, body: JSON.stringify({ "workspace": "665f1c2ab3e4d5f6a7b8c9d0", "question": "What did we decide about pricing?" }), }); const data = await res.text();

import os import requests r = requests.post( "https://api.markdrop.in/api/v1/meetings/ask", headers={"Authorization": f"Bearer {os.environ['MARKDROP_TOKEN']}"}, json={ "workspace": "665f1c2ab3e4d5f6a7b8c9d0", "question": "What did we decide about pricing?", }, ) r.raise_for_status() print(r.text)