POST/api/v1/me/documents/{slug}/analytics/ai/{kind}

Analyse with AI

Claude Haiku 5.5 reads the numbers (and your own content) and returns 3 to 5 findings that point at a section, timestamp, page or version, with rewrites (content), chapters (media) and a verdict with a confidence Markdrop computes (versions). Returns the saved analysis when there is one; send {"refresh": true} to analyse again. Below 20 sessions the model isn't called (state: thin). Counts towards your AI limits: 429 with code: limit and a reason when one is reached.

API token required20 per minute per IPMCP: analyze_document_engagement

Guide: AI insights for one link

Code samples and Try it

Path parameters

slugstringRequired
The document's address: the part after markdrop.in/.
kindstringRequired
One of content, media, pages, versions. One of content, media, pages, versions.

Query parameters

rangestring
The period to count: 7d, 30d, 90d or all. One of 7d, 30d, 90d, all. One of 7d, 30d, 90d, all. Default "30d".
internalinteger
From 0 to 1. Default 0.
verinteger
From 1 to 100,000.

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.

const res = await fetch("https://api.markdrop.in/api/v1/me/documents/k3x9q2m/analytics/ai/content?range=30d", { method: "POST", headers: { Authorization: `Bearer ${process.env.MARKDROP_TOKEN}`, }, }); const data = await res.json();

import os import requests r = requests.post( "https://api.markdrop.in/api/v1/me/documents/k3x9q2m/analytics/ai/content?range=30d", headers={"Authorization": f"Bearer {os.environ['MARKDROP_TOKEN']}"}, ) r.raise_for_status() print(r.json())