How to Use the New York Times MCP in Google ADK

Q: How can I use Google ADK to search for specific New York Times articles?

You instantiate an McpToolset with the MCP server URL and pass it to your LlmAgent. Your agent can then invoke the searcharticles tool with keywords and date ranges to find what it needs.

Q: Can a Gemini agent using Google ADK summarize New York Times best-seller lists?

Absolutely. The agent calls getbooklists to get the raw data for a list like 'hardcover-fiction'. Thanks to Gemini's large context, it can then process the entire list to generate a summary in one go.

Q: Is it possible to build a daily news briefing using Google ADK and the New York Times server?

Yes, that's a core use case. Your agent would call gettopstories for a few key sections. The results can be formatted and sent on, or even stored in Google Cloud Storage for a historical record.

Q: How do I manage API costs with this MCP server?

The toolnames filter in Google ADK is your first line of defense, preventing accidental calls to unwanted tools. You can also build logic into your agent to cache results from tools like getsections that don't change often.

Connect Gemini agents to the New York Times API with Google ADK, and pipe article data from this MCP server directly into your Google Cloud workflow.

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 Google ADK

Create your Vinkius account to connect New York Times to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query NYT Data for BigQuery

The `search_articles` and `get_archive` tools let your agent pull historical news data. You can specify keywords, dates, and sort order to get exactly what you need from the archive. Because you're using Google ADK, the agent can take the structured article data from this MCP Server and immediately pass it to another tool that writes to a BigQuery table. It's a straight shot from the newsroom to your data warehouse.

Long-Context News Analysis

Your agent can use `get_top_stories` to fetch the day's headlines or `get_most_viewed` to see what's trending. This gives it the raw material for creating summaries or reports. With Gemini's long-context window, your agent can pull dozens of articles and analyze them in a single prompt. This is perfect for building agents that generate in-depth market reports or track media narratives, all within the Google Cloud ecosystem.

Filter Tools with your Google ADK MCP Server

This server provides nine distinct tools, from `get_book_lists` to `get_movie_reviews`. That's a lot of surface area for an agent to manage. Google ADK lets you control this. When you initialize the `LlmAgent`, you can use the `tool_names` filter to expose only the tools you need, like `search_articles`. This tightens security and focuses your agent on a specific job.

Setup guide

Set up New York Times MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with New York Times tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="New York Times_agent",
    model="gemini-2.0-flash",
    instruction="You have access to New York Times tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You instantiate an `McpToolset` with the MCP server URL and pass it to your `LlmAgent`. Your agent can then invoke the `search_articles` tool with keywords and date ranges to find what it needs.

Absolutely. The agent calls `get_book_lists` to get the raw data for a list like 'hardcover-fiction'. Thanks to Gemini's large context, it can then process the entire list to generate a summary in one go.

Yes, that's a core use case. Your agent would call `get_top_stories` for a few key sections. The results can be formatted and sent on, or even stored in Google Cloud Storage for a historical record.

The `tool_names` filter in Google ADK is your first line of defense, preventing accidental calls to unwanted tools. You can also build logic into your agent to cache results from tools like `get_sections` that don't change often.

The server acts as a pass-through for New York Times article data and metadata. It doesn't store your queries or the article content it retrieves. Your Vinkius endpoint token authenticates you, keeping your NYT API key secure on the backend.

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