Nyt

السجل الرسمي أخرى

NYT MCP — wraps The New York Times Developer APIs (developer.nytimes.com)

ماذا يمكنك أن تفعل مع Nyt؟

  • search_articles(query, page?, begin_date?, sort?) — full-text search of NYT
  • top_stories(section?) — the current top stories for a section
  • books_bestsellers(list?) — the current bestseller list by list name
  • movie_reviews(query?, critics_pick?) — NYT movie reviews, optionally

التثبيت

أضف هذا إلى إعدادات MCP في عميلك (Claude Desktop: claude_desktop_config.json، وCursor: ‏.cursor/mcp.json، ويستخدم VS Code وغيره الصيغة نفسها «mcpServers»).

Remote (streamable-http)
Claude Code
claude mcp add --transport http nyt 'https://gateway.pipeworx.io/nyt/mcp'
إعداد JSON (Claude Desktop وCursor وVS Code)
{
    "mcpServers": {
        "nyt": {
            "type": "http",
            "url": "https://gateway.pipeworx.io/nyt/mcp"
        }
    }
}

التوثيق

مأخوذ من ملف README للمشروع على GitHub ويُحدَّث أسبوعيًا. تفتح الروابط على GitHub.

المحتويات
  1. @pipeworx/nyt
  2. Tools
  3. Auth
  4. Licence terms (read 2026-09-14, fleet #1977; resolved 2026-09-15, fleet #1980)
  5. Data sources
  6. Quick Start
  7. No MCP client? Call it over HTTP
  8. Standalone (no gateway account)
  9. Using with ask_pipeworx
  10. More
  11. License

@pipeworx/nyt

New York Times Developer APIs: article search, top stories by section, bestseller lists and movie reviews, as headlines, abstracts, bylines and nytimes.com URLs.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

  • search_articles(query, page?, begin_date?, sort?) — full-text search of NYT articles (Article Search API); 10 results per page, newest first by default. Exposed on the gateway as nyt_search_articles (eight packs export a search_articles; the bare name is ambiguous).
  • top_stories(section?) — the current top stories for a section (home, world, business, technology, science, health, sports, arts, …).
  • books_bestsellers(list?) — the current bestseller list by list name (hardcover-fiction, hardcover-nonfiction, combined-print-and-e-book-fiction, …): rank, title, author, publisher, weeks on list.
  • movie_reviews(query?, critics_pick?) — NYT movie reviews, optionally filtered to Critics' Picks.

Auth

Platform key (PLATFORM_NYT_KEY) with BYO override via _apiKey. The key is sent as the api-key query parameter. Upstream limits per API (portal FAQ #11): 500 requests per day and 5 requests per minute; the pack has no backoff, so a tight agent loop can hit the per-minute ceiling.

Licence terms (read 2026-09-14, fleet #1977; resolved 2026-09-15, fleet #1980)

The NYT API Terms of Use are non-commercial only, and the portal FAQ defines "commercial" to include "using our content inside an application that is paid or has a paid tier currently or in the future". They also forbid providing "archived or cached data sets containing Content to another person or entity" and cap any caching at 24 hours; the Branding guide requires the attribution "Data provided by The New York Times" (or the Times API logo) wherever the content is displayed, and unmodified headlines and links. The verbatim clauses, the bucket verdict and the traffic numbers are in docs/data/vendor-tos-audit.md (addendum 2026-09-14). Do not add a mirror or ingest of NYT content, and do not re-read the terms: the portal page is a JS shell, the text is served by /portals/api/sites/nyt-apigeex-prd-devportal/liveportal/page/terms.

Resolved 2026-09-15: Bruce chose zero-rate-attribute over asking NYT Licensing for written permission. The gateway pack entry carries zeroRated: true (0 credits, no pricing-v2 bracket advance) and every tool response carries an attribution field — "Data provided by The New York Times (developer.nytimes.com). Non-commercial use only under the NYT Developer Terms of Use; Pipeworx charges nothing for this data." This is good faith, not compliance: NYT's FAQ still calls a paid-tier app commercial, and §1(e)(v) still requires written permission to share access "whether for direct commercial or monetary gain or otherwise". Same posture already accepted for guardian/last-fm/watchmode/acled on 2026-08-18. Do not remove either mechanism without a fresh Bruce decision.

Data sources

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "nyt": {
      "url": "https://gateway.pipeworx.io/nyt/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/nyt/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/nyt_search_articles \
  -H 'Content-Type: application/json' \
  -d '{"query":"climate change","sort":"newest"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/nyt_search_articles. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "nyt": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-nyt"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-nyt

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Nyt data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

الأسئلة الشائعة

ما هو Nyt؟

NYT MCP — wraps The New York Times Developer APIs (developer.nytimes.com)

كيف أثبّت Nyt؟

يعمل كخادم بعيد. في Claude Code: claude mcp add --transport http nyt 'https://gateway.pipeworx.io/nyt/mcp'. وفي العملاء الآخرين، الصق إعداد JSON من هذه الصفحة في إعدادات MCP الخاصة بهم.

هل يحتاج Nyt إلى مفتاح API؟

لا يذكر إدراجه في السجل أي مفتاح أو سر إلزامي. قد تتطلب بعض الميزات حسابًا لدى الخدمة التي يتصل بها.

هل Nyt مفتوح المصدر؟

نعم. شيفرته متاحة على GitHub بترخيص MIT.

من يصون Nyt؟

ينشره pipeworx-io. يدرجه AI.tn لكنه لا يصونه ولا يوصي به.

من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك.