McKinsey APImckinsey.com ↗
Extract article titles, authors, publish dates, full body text, and exhibit images from any McKinsey.com article. Two endpoints, structured JSON output.
What is the McKinsey API?
The McKinsey.com API exposes 2 endpoints that return structured data from McKinsey articles and the Insights Store listing page. The get_article endpoint returns 5 fields per article — title, authors array, publish date, full body text, and exhibit image URLs — for any article URL you supply. The list_insights_store_articles endpoint returns the current set of featured titles and their URLs from the Insights Store.
curl -X GET 'https://api.parse.bot/scraper/ac9a62ce-db1a-4994-b137-54860a3d8045/get_article?url=https%3A%2F%2Fwww.mckinsey.com%2Finstitute-for-economic-mobility%2Four-insights%2Fthe-great-ownership-transfer-a-new-era-of-business-stewardship' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace mckinsey-com-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""Walkthrough: McKinsey Insights — list featured articles, then fetch full detail."""
from parse_apis.mckinsey_com_api import McKinsey, InvalidUrl
client = McKinsey()
# Browse the Insights Store curated list (capped to 5 items).
for summary in client.article_summaries.list(limit=5):
print(summary.title, summary.url)
# Drill into the first featured article for full content.
first = client.article_summaries.list(limit=1).first()
if first is not None:
article = first.details()
print(article.title)
print("Authors:", ", ".join(article.authors))
print("Published:", article.publish_date)
print("Exhibits:", len(article.exhibit_images))
print(article.body_text[:200])
# Direct lookup by known URL.
try:
detail = client.articles.get(url="https://www.mckinsey.com/capabilities/people-and-organizational-performance/our-insights/ai-transformations-run-on-trust")
print(detail.title, detail.publish_date)
except InvalidUrl as e:
print("Bad URL:", e.message)
print("exercised: article_summaries.list / details / articles.get")
Fetches a McKinsey article and returns its title, list of authors, publish date, full body text, and URLs of chart/figure/exhibit images embedded in the article. Accepts a full URL or path to any McKinsey article page. The body text is extracted from the embedded page data with HTML tags stripped. Exhibit images are extracted from the article's structured exhibit and image components (desktop versions); logos, icons, and avatars are excluded.
| Param | Type | Description |
|---|---|---|
| urlrequired | string | Full McKinsey article URL (e.g. https://www.mckinsey.com/institute-for-economic-mobility/our-insights/the-great-ownership-transfer-a-new-era-of-business-stewardship) or just the path portion starting with /. |
{
"type": "object",
"fields": {
"title": "Article headline",
"authors": "Array of author names",
"body_text": "Full article body as plain text with HTML stripped",
"publish_date": "ISO 8601 publish date",
"exhibit_images": "Array of absolute URLs for chart/figure/exhibit images embedded in the article body"
},
"sample": {
"data": {
"title": "The Great Ownership Transfer: A new era of business stewardship",
"authors": [
"Ken Yearwood",
"Shelley Stewart III"
],
"body_text": "At a glance\nA once-in-a-generation wave of ownership transitions is imminent.\nBy 2035, about six million small and medium-size businesses (SMBs) will face ownership transitions as baby boomers retire...",
"publish_date": "2026-02-26T00:00:00Z"
},
"status": "success"
}
}About the McKinsey API
Article Data via get_article
The get_article endpoint accepts a single required parameter, url, which can be any full McKinsey article URL. It returns the article title, an authors array of contributor names, a publish_date in ISO 8601 format, body_text as plain text with HTML stripped, and exhibit_images — an array of absolute URLs pointing to charts, figures, and exhibits embedded in the article body. This makes it straightforward to extract the full research text and associated visualizations in one call.
Insights Store Listing via list_insights_store_articles
The list_insights_store_articles endpoint takes no inputs and returns an articles array. Each object in that array contains a title string and a url string (absolute URL). The page content is curated by McKinsey and changes periodically, so results reflect the current featured set at call time. Navigation, footer, social, legal, pagination, and promotional links are excluded — only substantive article entries are returned.
Coverage and Scope
Both endpoints are scoped to mckinsey.com article content. get_article works against any article path on the domain — including sections like /industries, /capabilities, /featured-insights, and institute sub-sections. The exhibit_images field only includes images embedded in the article body; standalone report PDFs or appendix files are not surfaced.
The McKinsey API is a managed, monitored endpoint for mckinsey.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when mckinsey.com changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official mckinsey.com API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Build a research digest tool that pulls full
body_textfrom McKinsey articles on a given topic for summarization or indexing. - Track newly featured publications by polling
list_insights_store_articlesand diffing titles against a stored set. - Populate a content library with structured article metadata including
authors,publish_date, andtitlefor citation management. - Download
exhibit_imagesfrom articles to assemble visual reference collections for competitive analysis decks. - Feed
body_textfrom multiple articles into an LLM pipeline for thematic extraction or Q&A over McKinsey research. - Monitor which insights McKinsey surfaces on the Insights Store page as part of a broader media coverage tracking workflow.
- Archive article content with associated author attribution and dates for longitudinal research on business and economic topics.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 200 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
| Team | $300/mo | 20,000 | 300 req/min |
| Company | $1,000/mo | 100,000 | 500 req/min |
Each endpoint has a fixed posted price per successful call — most fall between 1 and 10 credits — shown on this API's page before you run it. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does McKinsey have an official public developer API?+
What does the get_article endpoint return beyond the article text?+
body_text, it returns the article title, an authors array, a publish_date in ISO 8601 format, and an exhibit_images array of absolute URLs for charts and figures embedded in the article body.Does the API cover McKinsey podcast transcripts or report PDFs?+
Can I filter list_insights_store_articles by topic, industry, or date?+
How fresh is the data returned by get_article?+
body_text, authors, and publish_date reflect what is live on mckinsey.com when you call the endpoint. McKinsey occasionally updates articles after initial publication, so repeated calls to the same URL may return revised content.