Integration

The New York Times integration

Read New York Times journalism metadata: search articles by keyword and Lucene filter query, pull every article of a given month from the archive back to 1851, read the stories currently on any section front or the home page, list the most emailed, shared and viewed articles of the last 1, 7 or 30 days, and fetch the weekly Best Sellers book lists. Responses carry headlines, abstracts or snippets, URLs, bylines, dates, Times Tags and images, never the full article text. The RSS feeds (XML) are not included. Authentication is an API key created on developer.nytimes.com, sent as the api-key query parameter; the API enforces per-minute and per-day rate limits.

Connect The New York Times How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in The New York Times.Built from the 9 The New York Times tools below, on the connection you add once.

What you can do with The New York Times

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Shared, 2 operations

list_most_shared_articlesList most shared articlesGETReturns the most shared NYTimes.com articles of the last 1, 7 or 30 days, with title, abstract, URL, section, byline, publication date, topic facets and image captions and credits (no image URLs).
list_most_shared_articles_by_typeList most shared articles by typeGETReturns the most shared NYTimes.com articles of the last 1, 7 or 30 days on one sharing channel; facebook is the only share type the API documents.

Articlesearch, 1 operation

search_articlesSearch articlesGETSearches New York Times articles by keywords (q) and filter query (fq), optionally between two dates. Returns 10 articles per page with headline, snippet, URL, byline, Times Tags and publication date; up to 100 pages.

Emailed, 1 operation

list_most_emailed_articlesList most emailed articlesGETReturns the most emailed NYTimes.com articles of the last 1, 7 or 30 days, with title, abstract, URL, section, byline, publication date, topic facets and image captions and credits (no image URLs).

List, 1 operation

get_best_sellers_listGet best sellers listGETReturns the books on one Best Sellers list for a print date, or the latest edition when date is current. Each book has its rank, last week's rank, weeks on the list, ISBN, title, author, publisher and an Amazon link.

Overview, 1 operation

get_best_sellers_overviewGet best sellers overviewGETReturns every New York Times Best Sellers list with all its books for one print date (the current lists when published_date is omitted). Each list carries the list_name_encoded value that get_best_sellers_list expects.

V1, 1 operation

get_archive_monthGet archive monthGETReturns the metadata of every New York Times article published in one month, back to 1851. The answer is large (often around 20 MB): to find a few articles, prefer search_articles with begin_date and end_date.

V2, 1 operation

list_top_storiesList top storiesGETReturns the articles currently on a NYTimes.com section front (arts, business, science, world and more) or, with section home, on the home page: title, abstract, URL, byline, dates, topic facets and images.

Viewed, 1 operation

list_most_viewed_articlesList most viewed articlesGETReturns the most viewed NYTimes.com articles of the last 1, 7 or 30 days, with title, abstract, URL, section, byline, publication date, topic facets and image captions and credits (no image URLs).

Use The New York Times from Claude Code, Cursor or Codex

Connect The New York Times in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its The New York Times operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect The New York Times

Create your workspace
Sign up free. Nothing to install.
Connect The New York Times once
Add your The New York Times connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.