Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Enables AI assistants to search New York Times Cooking recipes, fetch full recipes with ingredients and steps without login, and browse personal saved recipe box with optional authentication.

README.md

NYT Cooking MCP

An MCP server that lets an AI assistant (Claude, etc.) search New York Times Cooking, fetch full recipes, and browse your saved recipe box.

NYT Cooking has no official public API, so this reads the same JSON endpoints the website itself uses. The recipe paywall is enforced client-side, so searching and reading full recipes needs no login at all — only your personal saved recipe box requires a session cookie.

Tools

| Tool | Auth needed | Description | | --- | --- | --- | | search_recipes(query) | no | Search recipes by natural-language query. | | get_recipe(recipe_id) | no | Full recipe: ingredients, steps, time, rating. | | list_saved_recipes(page, per_page) | yes | Your saved recipe box. | | login(nyt_s_cookie, user_id) | — | Store credentials server-side and verify them. | | logout() | — | Delete the stored credentials. | | auth_status() | — | Check whether credentials are configured. |

Install & run

Requires Python 3.10+. With uv:

git clone https://github.com/bramboe/nyt-cooking-mcp
cd nyt-cooking-mcp
uv run nyt-cooking-mcp                                   # stdio (default)
uv run nyt-cooking-mcp --transport streamable-http --port 3001

Or with pipx / pip:

pipx install git+https://github.com/bramboe/nyt-cooking-mcp
nyt-cooking-mcp

Use with Claude Desktop / Claude Code

Add to your MCP config (claude_desktop_config.json, or via claude mcp add):

{
  "mcpServers": {
    "nyt-cooking": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/nyt-cooking-mcp", "nyt-cooking-mcp"]
    }
  }
}

Then ask: "search NYT Cooking for marry me chicken" or "get NYT recipe 1024503".

Saved recipes (optional login)

list_saved_recipes is the only tool that needs your account. NYT Cooking has no OAuth, so credentials are harvested once from your logged-in browser and persisted server-side (like a session token). Call the login tool with:

  1. nyt_s_cookie — value of the NYT-S cookie on cooking.nytimes.com

(DevTools → Application → Cookies).

  1. user_id — the regi_id value inside the regi_cookie.

login verifies the cookie with a live request and writes it to the credentials file (--credentials-file, default ~/.config/nyt-cooking-mcp/credentials.json). Environment variables NYT_S_COOKIE / NYT_USER_ID override the stored file. The NYT-S cookie is long-lived; when calls start returning auth_required, run login again.

Self-hosting as an always-on service

Run it as a systemd service over streamable-HTTP so it is always available:

# /etc/systemd/system/nyt-cooking-mcp.service
[Unit]
Description=NYT Cooking MCP Server
After=network.target

[Service]
User=nyt-cooking
ExecStart=/opt/nyt-cooking-mcp/.venv/bin/nyt-cooking-mcp \
    --transport streamable-http --host 0.0.0.0 --port 3001 \
    --credentials-file /var/lib/nyt-cooking-mcp/credentials.json
# Permit LAN access while keeping DNS-rebinding protection on (localhost always allowed):
Environment=NYT_MCP_ALLOWED_HOSTS=your.server.ip:*
Restart=on-failure

[Install]
WantedBy=multi-user.target

The HTTP endpoint is then http://your.server:3001/mcp. Put a reverse proxy (TLS) and an auth token in front before exposing it beyond your trusted network.

Disclaimer

For personal use. This is an unofficial tool not affiliated with The New York Times; respect NYT Cooking's Terms of Service and use your own account.

Support

If this project is useful to you, consider buying me a coffee ☕

![Buy Me A Coffee](https://buymeacoffee.com/bramboe)

License

MIT — see LICENSE.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.