How far back does the NYTimes archive go?

The article search API provides access to articles dating back to 1851. It is one of the most comprehensive historical newspaper archives available.

Can I get the actual text of the articles?

The API provides the headline, abstract (summary), snippet, and URL to the full article on NYTimes.com. Full text is not included in the API response but can be accessed via the provided link.

What sections are available for Top Stories?

You can access almost any section of the NYTimes, including home, world, politics, business, technology, sports, arts, health, and science. Use the get_sections tool to see the full list.

New York Times MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes

Name: New York Times
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 9 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect New York Times through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="New York Times Assistant",
            instructions=(
                "You help users interact with New York Times. "
                "You have access to 9 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from New York Times"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About New York Times MCP Server

Connect the New York Times API to any AI agent and unlock access to over 170 years of journalism — including breaking news, historical archives, best-seller lists, and cultural reviews.

The OpenAI Agents SDK auto-discovers all 9 tools from New York Times through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries New York Times, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Top Stories — Get the latest top stories for any section (World, Politics, Tech, Sports, etc.)
Article Search — Search the complete archive from 1851 to the present day with keywords and date filters
Most Popular — See what readers are emailing, sharing, and viewing the most
Best-Seller Lists — Retrieve current and historical book best-seller lists
Movie Reviews — Access thousands of movie reviews and critic summaries
Section Discovery — List all available sections and topics covered by the NYTimes

The New York Times MCP Server exposes 9 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect New York Times to OpenAI Agents SDK via MCP

Follow these steps to integrate the New York Times MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 9 tools from New York Times

Why Use OpenAI Agents SDK with the New York Times MCP Server

OpenAI Agents SDK provides unique advantages when paired with New York Times through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

New York Times + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the New York Times MCP Server delivers measurable value.

Automated workflows: build agents that query New York Times, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries New York Times, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through New York Times tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query New York Times to resolve tickets, look up records, and update statuses without human intervention

New York Times MCP Tools for OpenAI Agents SDK (9)

These 9 tools become available when you connect New York Times to OpenAI Agents SDK via MCP:

get_archive

Get all articles for a specific month

get_book_lists

"list_name_encoded" is the list slug (e.g., "hardcover-fiction"). Optional date is YYYY-MM-DD. Get current or historical best-seller lists

get_most_emailed

Period can be 1, 7, or 30 days. Get the most emailed articles for a specific period

get_most_shared

Period can be 1, 7, or 30 days. Get the most shared articles on social media

get_most_viewed

Get the most viewed articles

get_movie_reviews

Optional "query" filters by movie title. Search for movie reviews in the NYTimes archive

get_sections

List all available news sections

get_top_stories

g., home, world, politics, technology, sports). Use get_sections to see available options. Get top stories for a specific section

search_articles

Use "q" for keywords, "begin_date" and "end_date" for date ranges (YYYYMMDD), and "sort" for "newest", "oldest", or "relevance". Search for articles using keywords, date ranges, and sorting

Example Prompts for New York Times in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with New York Times immediately.

"Show me today's top world news."

"What is the #1 Hardcover Fiction book this week?"

"Find movie reviews for 'The Godfather'."

Troubleshooting New York Times MCP Server with OpenAI Agents SDK

Common issues when connecting New York Times to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

New York Times + OpenAI Agents SDK FAQ

Common questions about integrating New York Times MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.