How to Use the News MCP in AutoGen

Q: How do AutoGen agents resolve conflicting News reports?

One agent fetches headlines with gettopheadlines while a critic agent uses searcheverything to find alternative perspectives, debating the differences until they reach a consensus.

Q: How does AutoGen pass News search queries between agents?

The agent using searcheverything returns the raw article list as a string, which AutoGen automatically injects into the group chat history for other agents to read.

Let your AutoGen agents debate and verify breaking news stories using live global coverage sources.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect News MCP to AutoGen

Create your Vinkius account to connect News 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 News with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-examine live events with an AutoGen MCP Server

The `get_top_headlines` tool gives your multi-agent team instant access to breaking global news. In AutoGen, one agent can fetch the raw headlines while another agent analyzes them for bias or conflicting reports. This setup lets you build consensus-driven news aggregators. Your agents debate the validity of a breaking story, using the live headlines as concrete evidence to back up their arguments.

Fact-check historical claims across millions of articles

The `search_everything` tool allows your agents to run advanced boolean searches across 150,000 global sources via this MCP integration. An analyst agent can construct precise search queries to verify claims made by other agents in your conversation group. If a research agent makes an unverified claim, the fact-checking agent triggers this search tool to find corroborating articles, ensuring your final report is backed by real-world documentation.

Evaluate source credibility before debating

The `list_sources` tool provides the full directory of active news publishers. Your AutoGen supervisor agent can check this list to verify if a source cited during a debate is reputable. This prevents your agents from relying on untrustworthy media. The supervisor agent cross-references the source list and instructs the search agent to only pull articles from approved publishers.

Setup guide

Set up News 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 News 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="News_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent News 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="News_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent News 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 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 News 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 News MCP in AutoGen

One agent fetches headlines with `get_top_headlines` while a critic agent uses `search_everything` to find alternative perspectives, debating the differences until they reach a consensus.

Yes, you can register the MCP tools specifically with your researcher agent while keeping your writer and editor agents focused purely on synthesis.

The agent using `search_everything` returns the raw article list as a string, which AutoGen automatically injects into the group chat history for other agents to read.

Yes, your agents can use boolean operators like AND, OR, and NOT within their generated search strings to narrow down results.

Yes. The server only receives the specific search queries and retrieved news articles generated by the tools, never your internal agent chat logs or system prompts, running entirely in a secure, isolated sandbox.

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