How to Use the NewsCatcher MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system search historical NewsCatcher data?

Yes, you run the searchnews tool with specific keyword and date parameters. The agent handles the query formatting and returns the matched articles directly to your python environment.

Q: Do the built-in guardrails work with the clustering tool?

They do. When your agent calls getnewsclusters, the framework validates the parameters before execution. You control exactly how the agent interacts with the grouped stories.

Build production-ready news tracking systems with OpenAI Agents SDK and real-time media ingestion.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsCatcher MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Auto-Discovering News Monitors

The `get_latest_news` tool connects your OpenAI Agents SDK system directly to global news feeds. You pass a topic or specific source, and the agent pulls the most recent articles matching those exact parameters. Because this MCP setup handles tool discovery automatically, you don't waste time writing integration code. Your agent sees the tool, understands the required parameters like country codes, and starts fetching data immediately while logging every action to your OpenAI dashboard.

Route Complex Stories Across Agents

Using the `get_news_clusters` tool, your agents group related stories into distinct narratives. This prevents your system from getting overwhelmed by identical reports from fifty different outlets covering the exact same event. You can set up handoffs based on these clusters. One agent handles the initial grouping, then passes specific thematic bundles to specialized agents for deeper analysis. The built-in guardrails ensure the agents only act on verified clusters, keeping your production pipeline stable.

Filter Noise with This MCP Server

The `list_sources` tool lets you restrict your agent's diet to specific publications based on language or topic. You define the boundaries, and the framework enforces them before any search executes. When you combine this with `search_news`, your agent executes highly targeted queries against millions of articles. The agent sorts the results by relevancy or date, giving you a clean, traceable output that fits perfectly into your enterprise workflow.

Setup guide

Set up NewsCatcher 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 NewsCatcher tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NewsCatcher 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="NewsCatcher Agent",
            instructions="You have access to NewsCatcher 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 NewsCatcher. 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 NewsCatcher 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 NewsCatcher MCP in OpenAI Agents SDK

You initialize an MCPServerStreamableHttp instance with your server URL. Pass it into the mcp_servers list when creating your Agent constructor.

Yes, you run the search_news tool with specific keyword and date parameters. The agent handles the query formatting and returns the matched articles directly to your python environment.

Setting cacheToolsList=True stops the agent from re-discovering the tools on every single request. This cuts down latency and keeps your production app running fast.

They do. When your agent calls get_news_clusters, the framework validates the parameters before execution. You control exactly how the agent interacts with the grouped stories.

Your search queries and source filtering preferences stay within your configured infrastructure. The protocol acts as a strict boundary, meaning the news aggregation endpoint only sees the parameters needed to return the articles, without accessing your broader application state.

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