How to Use the New York Times MCP in AutoGen

Q: How do AutoGen agents share New York Times tool outputs?

When one AutoGen agent calls gettopstories, the resulting New York Times JSON is posted to the group chat history. All other AutoGen agents in the conversation can immediately read and analyze that New York Times data.

Q: Can I limit which AutoGen agent has access to New York Times search tools?

Yes, you can register searcharticles specifically with your research AutoGen agent while keeping other agents restricted. This prevents unnecessary New York Times API calls and keeps your AutoGen conversations organized.

Enable multi-agent AutoGen debates powered by real-time New York Times reporting and archives via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect New York Times MCP to AutoGen

Create your Vinkius account to connect New York Times to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup New York Times with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel AutoGen agent debates with live New York Times stories

The `get_top_stories` tool injects real-time events into your AutoGen multi-agent conversations so agents can debate current New York Times news. One AutoGen agent can retrieve the New York Times headlines while another analyzes the political bias of the coverage. This multi-agent setup ensures that your AutoGen system doesn't rely on a single model's interpretation of New York Times events. The AutoGen framework coordinates the dialogue, using the live New York Times headlines to ground the discussion in real-world facts.

Let AutoGen agents audit historical New York Times archives

The `search_articles` tool allows your specialized AutoGen agents to collaborate on deep historical research using New York Times records. A research AutoGen agent can fetch New York Times articles from specific date ranges, while an auditor agent verifies the sources. This collaborative loop helps prevent the AutoGen agents from accepting incomplete New York Times search results. They will request more New York Times data using different keywords until the AutoGen conversation reaches a consensus on the topic.

Analyze viral New York Times trends with AutoGen agents

The `get_most_emailed` tool provides trending metrics that your AutoGen agents can use to study public interest in New York Times coverage. An analyst AutoGen agent can compare these viral New York Times stories against the cultural rankings from `get_book_lists`. Having multiple AutoGen agents debate the correlation between New York Times email virality and book sales yields deeper insights. The AutoGen adapter handles the schema conversion, so your agents can call these New York Times MCP tools without formatting errors.

Setup guide

Set up New York Times MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes New York Times tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="New York Times_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent New York Times data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="New York Times_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent New York Times data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by New York Times. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect New York Times now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about New York Times MCP in AutoGen

When one AutoGen agent calls `get_top_stories`, the resulting New York Times JSON is posted to the group chat history. All other AutoGen agents in the conversation can immediately read and analyze that New York Times data.

Yes, you can register `search_articles` specifically with your research AutoGen agent while keeping other agents restricted. This prevents unnecessary New York Times API calls and keeps your AutoGen conversations organized.

You can configure your AutoGen critic agent to monitor New York Times tool call frequency and pause the conversation if limits are near. This keeps your AutoGen agents from hitting publisher API thresholds during intense deliberations.

The MCP Server supports both stdio and streamable HTTP transports for connecting to AutoGen to pull New York Times data. You define the server parameters in your Python code, and the tool adapter maps the New York Times schemas automatically.

Only the explicit New York Times search queries and filter parameters sent via tools like `get_archive` reach the publisher's API. Your internal AutoGen agent debates, prompts, and conversation logs remain strictly confined to your local environment, completely isolated from the MCP Server.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript