How to Use the NewsAPI MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK use NewsAPI to find breaking business news?

Your agent can periodically call getheadlinesbycategory with the 'business' category. When it finds a new headline, it can use the searcharticles tool to gather more context from different sources.

Q: Can I filter news by country or language with my agent?

Yes. The agent can use the getheadlinesbycountry tool with a country code like 'us' or 'gb'. To filter by language, it would use the getarticlesbylanguage tool with a code like 'en' or 'es'.

Q: What's the best way to search historical articles with NewsAPI and the OpenAI Agents SDK?

The searcharticles tool is built for this. Your agent can call it with specific keywords, date ranges, and domains to pull a precise set of historical articles from the NewsAPI database for analysis.

Q: How does the NewsAPI MCP Server show up in the OpenAI dashboard?

Every tool call your agent makes—like getrecentarticles—is logged as a step in the agent's run. You'll see the exact inputs and outputs from the NewsAPI server in your trace, which is great for debugging.

Build production news agents with the OpenAI Agents SDK that query real-time data from over 150,000 sources.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsAPI MCP to OpenAI Agents SDK

Create your Vinkius account to connect NewsAPI to OpenAI Agents SDK 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 NewsAPI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor news and trigger agent workflows

Give your agent the ability to watch the news. It can use `get_headlines_by_category` to monitor for breaking stories in a specific vertical, like tech or finance. When a relevant headline appears, it can trigger another specialized agent to dig deeper. That second agent can then use `search_articles` to find related coverage and build a full report. With the OpenAI dashboard, you get a full trace of this handoff, so you always know exactly what your agents are doing and why. It's a clear, auditable trail for production systems.

Run safe, validated news queries

Your agent gets access to powerful search tools, but you stay in control. Before your agent executes a call to `get_articles_from_domains` or `search_headlines`, OpenAI's built-in guardrails can validate the action. This prevents your agent from running nonsensical or unintended queries. You define the rules. The framework enforces them. This means you can confidently deploy agents that interact with real-world news data without worrying about them going off the rails. It’s a safety net for autonomous operations.

Auto-discover tools from this MCP Server

You don't need to manually define each NewsAPI function for your agent. Just point the OpenAI Agents SDK to the Vinkius endpoint for this MCP Server. It automatically discovers all 10 tools, from `list_sources` to `get_popular_articles`. Your agent immediately understands what it can do—search, list, and get headlines. Setting `cacheToolsList=True` makes this process even faster on subsequent runs. You write less boilerplate code and get to the real work faster.

Setup guide

Set up NewsAPI MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NewsAPI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NewsAPI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NewsAPI tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NewsAPI Agent",
            instructions="You have access to NewsAPI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 NewsAPI. 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 NewsAPI 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 NewsAPI MCP in OpenAI Agents SDK

Your agent can periodically call `get_headlines_by_category` with the 'business' category. When it finds a new headline, it can use the `search_articles` tool to gather more context from different sources.

Yes. The agent can use the `get_headlines_by_country` tool with a country code like 'us' or 'gb'. To filter by language, it would use the `get_articles_by_language` tool with a code like 'en' or 'es'.

The `search_articles` tool is built for this. Your agent can call it with specific keywords, date ranges, and domains to pull a precise set of historical articles from the NewsAPI database for analysis.

Every tool call your agent makes—like `get_recent_articles`—is logged as a step in the agent's run. You'll see the exact inputs and outputs from the NewsAPI server in your trace, which is great for debugging.

The server processes article metadata like headlines, source names, author, and URLs. Your data is handled within a Vinkius zero-trust environment. Each server runs in an ephemeral, single-use sandbox, and all auth is managed by a single endpoint token.

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